WO1986006527A1 - Skin-pattern recognition method and device - Google Patents

Skin-pattern recognition method and device Download PDF

Info

Publication number
WO1986006527A1
WO1986006527A1 PCT/GB1986/000219 GB8600219W WO8606527A1 WO 1986006527 A1 WO1986006527 A1 WO 1986006527A1 GB 8600219 W GB8600219 W GB 8600219W WO 8606527 A1 WO8606527 A1 WO 8606527A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
pattern
skin
photo
print
Prior art date
Application number
PCT/GB1986/000219
Other languages
French (fr)
Inventor
Peter Brian Denyer
Original Assignee
The Quantum Fund Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by The Quantum Fund Ltd. filed Critical The Quantum Fund Ltd.
Publication of WO1986006527A1 publication Critical patent/WO1986006527A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/1365Matching; Classification
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00Individual registration on entry or exit
    • G07C9/20Individual registration on entry or exit involving the use of a pass
    • G07C9/22Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
    • G07C9/25Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
    • G07C9/257Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00Individual registration on entry or exit
    • G07C9/30Individual registration on entry or exit not involving the use of a pass
    • G07C9/32Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition

Definitions

  • This invention relates to a method for establishing the authenticity of a person presenting oneself to a recognition station.
  • the invention relies on an arrange ⁇ ment for capturing a skin-pattern which is unique to the person in question (e.g. a toe, finger or palm print) and presenting this in digital form so that it can be compared with a memory-stored digitised skin pattern characteristic of the person.
  • the invention is expected to find applications in a number of different areas. An important one is to verify the identity of a person presenting a credit or bankers card at a point-of-sale location.
  • a skin-pattern authentication method can form the basis for an electronic lock, limiting access to a secure location only to individuals authorised to enjoy such access.
  • a skin-pattern authentication method can form the basis for an identity confirm ⁇ ation device to enable secure computer and information access at isolated stations in an electronic or optical network.
  • a method of authenticating a person by comparing information from a currently taken skin-pattern with stored information from a previously taken skin-pattern is characterised in that the currently taken skin-pattern is produced on a contact surface, an image of the print of the skin pattern on the contact surface is projected onto a photo- detector device, the intensity variations of the print image in at least one region thereof impinging on the photo-detector device is assessed .
  • digital • form in a multiplicity of different sub-regions of the or each said region to create a first digital signal train a second digital signal train is derived from the stored skin pattern information and the first and second signal trains are compared to determine the degree of coincidence therebetween, an assessment of the determined degree being used to decide whether the currently-taken and stored skin patterns are sufficiently similar to authenti ⁇ cate the person.
  • the image of the skin pattern is created by making the contact surface, the hypotenuse face of a right angled prism and projecting an image of this pattern-contacted face onto a surface of the photo- detector device which is divided into a multiplicity of separate photon-sensitive areas, each representing one pixel of the projected image.
  • the degree of coincidence between the first and second signal trains is assessed on the basis of direct correlation and desirably by direct binary correlation.
  • the direct correlation is effected using, as the stored information, a reference template representing less than 10% of the full image of the curr ⁇ ently-taken skin pattern.
  • Possible misalignment between currently and pre- viously taken skin patterns can be allowed for by the use of multiple trial correlations over a range of stepped lateral movements and a range of discrete angular dis ⁇ placements of a reference template relative to the curr ⁇ ently taken skin pattern.
  • two or more tem ⁇ plates can be used and the direct correlation made while allowing relative translational and/or rotational move ⁇ ments between the two or more templates.
  • the invention also extends to a finger print capture device comprising a photo-detector device having a surface divided into a matrix of separate photosensitive areas, eac of which can monitor the light intensity of one pixel of an image projected thereon and means to project a fingerprint pattern onto said matrix-divided surface.
  • the device is characterised in that the fingerprint patt ⁇ ern is created on the hypotenuse face of a right angle prism, the prism, an illuminating source for the face, an optical system for projecting an image of the hypoten ⁇ use face onto the said matrix-divi ⁇ ed surface, and the photo-detector device being mounted together as a compo ⁇ site unit.
  • hypotenuse face of the prism in ⁇ cludes means to encourage consistently similar locations of fingers on the hypotenuse face.
  • the fingerprint capture device defined above can be used to create a first signal train from a real time image of a fingerprint of a presenter of a sheet member (e.g. a cheque or bankers/credit card) required for a cash transaction and can be associated with means to read from the sheet member the second signal train.
  • a sheet member e.g. a cheque or bankers/credit card
  • the fingerprint captive device can be used to create a first signal train from a real time image of a fingerprint of a person requiring verification, the capture device being linked to a remote data bank from which the second signal trains of finger ⁇ prints of many different persons can be generated and the local capture device being associated with means whereby a nominated person's second signal -train can be called up for comparison with an output of the local capture device.
  • the fingerprint capture device can be associated with the release mechanism of a normally-locked site access device.
  • Figure 1 shows the principle components of a skin- pattern authentication device based on the method of the invention
  • Figure 2 shows the preferred optical and photo- detector assembly for a skin-pattern capture device according to the invention
  • Figure 3 is an example of a typical fingerprint image captured by the device of Figure 2
  • Figures 4a and 4b show how a reference signal may be formed from a sparsely sampled template, Figure 4a being an enlarged example of part of a binary print image and Figure 4b showing how six samples may be selected and coded to form a template of this part of the image,
  • Figures 5a-5c show how a set of templates can be used to test for correlation at different places in the image space, Figure 5a showing an example of two adjacent templates, Figures 5b showing one example of a trial placement of the template set of Figure 5a to test for a match in the upper left of the image space with some anti-clockwise rotation and Figure 5c showing one example of a possible rearrangement of the templates in the posi- tion of Figure 5b, to accommodate for local image distor ⁇ tion, and
  • the invention is capable of operating with skin- patterns from a finger, thumb, toe or palm.
  • skin- patterns from a finger, thumb, toe or palm.
  • the following description will refer exclusively to fingerprints but this should not be taken to represent a limitation of the invention to such prints.
  • a photo-detector 20 receives a fingerprint image on a photo-sensitive surface thereof and feeds an elec ⁇ trical signal representative of the image to an image preprocessor/discriminator unit 21.
  • the output of the unit 21 can be used as a record of the individual provid ⁇ ing the fingerprint (in which case it is processed in . a template generator 22 and retained in a store 23) or as a representation of a real time image for comparison with a record in the template store 23. The comparison is effected in a unit 24.
  • Calling-up information from the store 23 and controlling the units 21 and 24 is per- formed by a system controller 25 actuated (at least as shown in Figure 1) by a keypad/card reader 26 and supply ⁇ ing an output signal (indicating recognition/or non- recognition) to an indicator 27.
  • a compact optical/electronic system for sensing fingerprint images is shown in Figure 2.
  • a fingerpad 1 is presented to face 2 of a prism 3.
  • the further face 4 of said prism, or any surface perpendicularly below said further face, is blackened.
  • the image viewed through face 10 of the prism is a dark image of the face 4, internally reflected by the face 2.
  • the process of internal reflection is disturbed and inci- dent light from any direction is scattered at the points of contact. This gives rise to a bright image of the ridge pattern of the fingerpad 1 as viewed through the face 10.
  • the image of the fingerprint is focussed onto a light-sensitive surface of a photo-detector imaging device 8 through a lens 5.
  • a further prism 6 serves as a reflec ⁇ tor to alter the angle of the optical axis so that the optical structure, comprising the lens 5 and prism 6, may lie parallel to a circuit board 9. This facilitates a relatively flat mechanical structure and permits the circuit board to support both the imaging device 8 and the optical structure 3, 5, 6 as one unit.
  • the reflecting properties of the prism 6 may be enhanced by silvering face 7, or by replacing this prism entirely with a mirror in the plane of the face 7. Also the optical principle of the system may be preserved if a pinhole aperture is used in place of the lens 5.
  • the source of the incident light may be provided by ambient light through any of the available faces of the prism 3, or by one or more artificial light sources mounted in the vicinity of the prism 3.
  • a light source 12 is used and a glass plate (or partly- silvered mirror) 11 has a surface 13 from which the light from the source 12 is fed into the prism 3.
  • the viewing angle set by the relation ⁇ ship between the device 8, the prisms 3 and 6 and the lens 5 is preferably below the critical angle causing total internal reflection at the hypotenuse face 2 of the prism 3.
  • the viewed image is normally black, except where ridges of the fingerprint make contact with the surface of the prism, causing scattered light to form a bright image in the viewing direction.
  • a typical such image is shown at 15 in Figure 3.
  • the light-sensitive surface of the photo-detector device 8 is divided into a multiplicity of photon-sensi ⁇ tive areas, each representing one pixel of the projected image 15 shown in Figure 3.
  • the photo-detector device 8 When the print image is required in a high-contrast (black/white) form, the photo-detector device 8 should include, or be followed by, a binary discriminator to decide the value of each sample point in the image 15. This requirement may be met by using a Dynamic Random Access Memory (DRAM) device as a combined photo-detector and binary discriminator. Irrespective of end use, the production cost of a recognition system according to the invention may be reduced by using a DRAM imager/ discriminator in place of a conventional solid-state photo-detector device.
  • DRAM Dynamic Random Access Memory
  • an image of the fingerprint is required in a simple binary (black and white) representation.
  • the process of binary discrimination may occur within the photo-detector device itself by applying a threshold of decision uniformly across the received image. Alter- natively the discrimination may occur in a separate pro ⁇ cess whereby an analogue representation of the image is converted to a multiple-level digital form and a threshold of discrimination is derived separately for each sample point, or area of samples, according to the average values of the samples within the local neighbour ⁇ hood.
  • This process is known as adaptive thresholding and serves to cancel gross variations in the intensity of the print image due to differing surface conditions and contact pressures.
  • An important aspect of this invention resides in - the recognition process. To achieve the aims of fast response time and low hardware cost, it is desirable that this should involve minimal computation.
  • Existing schemes based on minutiae extraction and comparison are markedly expensive in this context. They have developed through earlier work on print matching for police and Court applications. This degree of analysis may be un ⁇ warranted in a consummer application, where the error rate needs to be sufficiently low to deter a fraud attempt, but need not be so low as to offer an absolute guarantee of identity.
  • the preferred recognition algorithm employed is a form of "binary correlation" .
  • this involves comparing a binarised image of the print with a binary reference image, and counting the coincidences (black with black, and white with white).
  • This is an elementary computational exercise which may be executed at high speed in electronic hardware.
  • this simple form has several practical disadvantages. Firstly, where the reference is a whole print image (per ⁇ haps 64K bits of information), the storage requirement is undesirably large. Secondly, the print image may not be consistently aligned with the optical path of the sensing mechanism, so that both translational and rotational misalignment is possible.
  • the print image may differ marginally from trial to trial according to the lighting conditions, the pressure of contact and the condition of the skin (dry or greasy). Finally, the print may be distorted due to stretching of the skin according to the direction and force of contact.
  • a reference template is derived which contains relatively few samples chosen in a fixed pattern from the print image, for the purpose of example, suppose that we use a reference template of 100 points, selected from an image of 256 x 256 pixels. Both the storage and compu ⁇ tation times using this template are reduced in the ratio 100:65,536 over the use of the full image. The possible combinations of a 100-bit template are nevertheless suff ⁇ icient to ensure a small likelihood of significant corre ⁇ lation, except for an identical' print. "
  • Misalignment of the print is accommodated by the use of multiple trial correlations over a range of potential positions and orientations. For example, later ⁇ al movements up to 64 pixels in any direction in one pixel steps, and rotational movements up to +/- 5 degrees in one degree steps, may be examined in a set of approxi ⁇ mately 180,000 trials. A success in any one trial may be taken as an indication of a match at a particular position and orientation.
  • the extent of the misalignment, and thus the number of potential trials requiired, may be restricted by the use of a raised moulding 14 on the surface of the prism to which the finger is presented.
  • This moulding acts as a guide to maintain the area of contact in an approx ⁇ imately consistent position and orientation. Marginal variations in the images obtained from the same print may still arise. These are accommodated by recoding the reference template to indicate the most likely areas of variation, and then inhibiting these samples from the correlation. The samples most frequently effected are those that lie close to the ridge/trough (white/black) transitions.
  • the reference template contains a set of samples, each marked “black”, “white” or “indeterminate” ("b", “w” and “?” in Figure 4b).
  • matches and mismatches are counted from the determinate ("b" and "w” ) samples only. These samples represent black and white regions at the cores of troughs and ridges, where the same value may consistently be expected.
  • the final correlation score may then be taken as the ratio of this count.to the potential number of determinate candidates,
  • the derived refer ⁇ ence template(s) for an individual may be recorded onto the magnetic strip 30 on the reverse side of a cheque or credit card 31.
  • a self-contained unit 32 at the point of sale may then be used to read this reference from the magnetic strip in a card reader 33, form a real ⁇ time image of the fingerprint of the person presenting the card in a print reader 34, and proceed to verify his identity as the true owner of the card in a matcher unit 35.
  • a further variation on the above is to allow the consumer to remember the pass-number, to be keyed in at a keyboard 37 at the point-of-sale. This is shown in Figure 9 and removes the requirement for the issue and maintenance of a card system, and obviates the require ⁇ ment for any card reader at the point-of-sale.
  • the recognition system disclosed here may further be used as the basis of a secure remote computer access system.
  • identity of a user at a remote terminal may be confirmed by providing print-sensor equip ⁇ ment at the terminal site capable of transmitting an image of the print, or a reduced template form of the image, to the host machine for verification.
  • the recognition system may further be used as the basis of a secure doorlock or site access device.
  • a library of templates corresponding to the set of people to. be permitted entry may be stored in the lock device, or remotely.
  • the user may present a card containing magnetic or optically encoded identity infor ⁇ mation, or may enter an identity code at a keypad, which information is used to bring forth reference templates which are used to verify his identity.

Abstract

A method of authenticating a person by comparing information from a currently taken skin-pattern with stored information from a previously taken skin-pattern is characterised in that the currently taken skin-pattern is produced on a contact surface, an image of the print of the skin pattern on the contact surface is projected onto a photo-detector device (20), the intensity variations of the print image in at least one region thereof impinging on the photo-detector device is assessed in digital form in a multiplicity of different sub-regions of the or each said region to create (in unit 21) a first digital signal train, a second digital signal train is derived from the stored skin pattern information (in store 23) and the first and second signal trains are compared (in 24) to determine the degree of coincidence therebetween, an assessment of the determined degree being used to decide (on indicator 27) whether the currently-taken and stored skin patterns are sufficiently similar to authenticate the person.

Description

Skin-pattern recognition method and device Technical Field
This invention relates to a method for establishing the authenticity of a person presenting oneself to a recognition station. The invention relies on an arrange¬ ment for capturing a skin-pattern which is unique to the person in question (e.g. a toe, finger or palm print) and presenting this in digital form so that it can be compared with a memory-stored digitised skin pattern characteristic of the person.
The invention is expected to find applications in a number of different areas. An important one is to verify the identity of a person presenting a credit or bankers card at a point-of-sale location.
Alternatively a skin-pattern authentication method according to the invention can form the basis for an electronic lock, limiting access to a secure location only to individuals authorised to enjoy such access.
A skin-pattern authentication method according to the invention can form the basis for an identity confirm¬ ation device to enable secure computer and information access at isolated stations in an electronic or optical network.
Discussion of Prior Art
The objective of individual recognition by finger¬ prints is not unique to this invention. Other approaches have been disclosed in GB-A-1509095, GB-A-1583386, US- A-4015240 and US-A-4310827 and in published literature. Those most frequently cited involve a preliminary analysis of the image to determine the location of minutiae identi¬ fied with ridge endings, bifurcations, etc.. The pattern of the minutiae is then matched against a reference patt- ern. The process described in this specification is not related to these forms of recognition; it is not based on any special analysis or property of the minutiae.
The use of a prism to reveal the image of a finger¬ print is not unique to this invention (see for example US-A-4015240).
Summary of the Invention
According to one aspect of the invention, a method of authenticating a person by comparing information from a currently taken skin-pattern with stored information from a previously taken skin-pattern is characterised in that the currently taken skin-pattern is produced on a contact surface, an image of the print of the skin pattern on the contact surface is projected onto a photo- detector device, the intensity variations of the print image in at least one region thereof impinging on the photo-detector device is assessed .in digital • form in a multiplicity of different sub-regions of the or each said region to create a first digital signal train, a second digital signal train is derived from the stored skin pattern information and the first and second signal trains are compared to determine the degree of coincidence therebetween, an assessment of the determined degree being used to decide whether the currently-taken and stored skin patterns are sufficiently similar to authenti¬ cate the person.
The process of direct correlation which is utilised in the carrying out of the method of this invention, is conventionally discarded as impractical on the grounds of image variation and distortion. The method disclosed here overcomes the difficulties associated with direct correlation and offers a unique practical solution for speedy and economical recognition hardware.
Suitably the image of the skin pattern is created by making the contact surface, the hypotenuse face of a right angled prism and projecting an image of this pattern-contacted face onto a surface of the photo- detector device which is divided into a multiplicity of separate photon-sensitive areas, each representing one pixel of the projected image.
Preferably the degree of coincidence between the first and second signal trains is assessed on the basis of direct correlation and desirably by direct binary correlation.
Conveniently the direct correlation is effected using, as the stored information, a reference template representing less than 10% of the full image of the curr¬ ently-taken skin pattern.
Suitably only determinate samples^ of the image which can clearly be categorised as a binary "1" or a binary "O" are used for the correlation, all "indeterminate" samples being discounted.
Possible misalignment between currently and pre- viously taken skin patterns can be allowed for by the use of multiple trial correlations over a range of stepped lateral movements and a range of discrete angular dis¬ placements of a reference template relative to the curr¬ ently taken skin pattern.
To compensate for possible stretching of the skin during the taking of the skin pattern two or more tem¬ plates can be used and the direct correlation made while allowing relative translational and/or rotational move¬ ments between the two or more templates.
The invention also extends to a finger print capture device comprising a photo-detector device having a surface divided into a matrix of separate photosensitive areas, eac of which can monitor the light intensity of one pixel of an image projected thereon and means to project a fingerprint pattern onto said matrix-divided surface. The device is characterised in that the fingerprint patt¬ ern is created on the hypotenuse face of a right angle prism, the prism, an illuminating source for the face, an optical system for projecting an image of the hypoten¬ use face onto the said matrix-diviαed surface, and the photo-detector device being mounted together as a compo¬ site unit.
Conveniently the hypotenuse face of the prism in¬ cludes means to encourage consistently similar locations of fingers on the hypotenuse face.
The fingerprint capture device defined above can be used to create a first signal train from a real time image of a fingerprint of a presenter of a sheet member (e.g. a cheque or bankers/credit card) required for a cash transaction and can be associated with means to read from the sheet member the second signal train.
In another mode of use, the fingerprint captive device can be used to create a first signal train from a real time image of a fingerprint of a person requiring verification, the capture device being linked to a remote data bank from which the second signal trains of finger¬ prints of many different persons can be generated and the local capture device being associated with means whereby a nominated person's second signal -train can be called up for comparison with an output of the local capture device.
The fingerprint capture device can be associated with the release mechanism of a normally-locked site access device. Brief Description of the Drawings
The invention will now be further described, by way of example, with reference to the accompanying draw¬ ings, in which:
Figure 1 shows the principle components of a skin- pattern authentication device based on the method of the invention,
Figure 2 shows the preferred optical and photo- detector assembly for a skin-pattern capture device according to the invention,
Figure 3 is an example of a typical fingerprint image captured by the device of Figure 2,
Figures 4a and 4b show how a reference signal may be formed from a sparsely sampled template, Figure 4a being an enlarged example of part of a binary print image and Figure 4b showing how six samples may be selected and coded to form a template of this part of the image,
Figures 5a-5c show how a set of templates can be used to test for correlation at different places in the image space, Figure 5a showing an example of two adjacent templates, Figures 5b showing one example of a trial placement of the template set of Figure 5a to test for a match in the upper left of the image space with some anti-clockwise rotation and Figure 5c showing one example of a possible rearrangement of the templates in the posi- tion of Figure 5b, to accommodate for local image distor¬ tion, and
Figures 6 to 9 show various ways of putting the method according to the invention into practice. Description of Preferred Embodiments
The invention is capable of operating with skin- patterns from a finger, thumb, toe or palm. For conven¬ ience, however, the following description will refer exclusively to fingerprints but this should not be taken to represent a limitation of the invention to such prints.
Referring to Figure 1, the basic components of hard¬ ware of a preferred arrangement required to operate the method of the invention are shown.
A photo-detector 20 receives a fingerprint image on a photo-sensitive surface thereof and feeds an elec¬ trical signal representative of the image to an image preprocessor/discriminator unit 21. The output of the unit 21 can be used as a record of the individual provid¬ ing the fingerprint (in which case it is processed in . a template generator 22 and retained in a store 23) or as a representation of a real time image for comparison with a record in the template store 23. The comparison is effected in a unit 24. Calling-up information from the store 23 and controlling the units 21 and 24 is per- formed by a system controller 25 actuated (at least as shown in Figure 1) by a keypad/card reader 26 and supply¬ ing an output signal (indicating recognition/or non- recognition) to an indicator 27.
A compact optical/electronic system for sensing fingerprint images is shown in Figure 2. A fingerpad 1, is presented to face 2 of a prism 3. The further face 4 of said prism, or any surface perpendicularly below said further face, is blackened. In the absence of any contact between the fingerpad 1 and the face 2, the image viewed through face 10 of the prism is a dark image of the face 4, internally reflected by the face 2. When the ridges of the fingerpad contact the face 2 however, the process of internal reflection is disturbed and inci- dent light from any direction is scattered at the points of contact. This gives rise to a bright image of the ridge pattern of the fingerpad 1 as viewed through the face 10.
The image of the fingerprint is focussed onto a light-sensitive surface of a photo-detector imaging device 8 through a lens 5. A further prism 6 serves as a reflec¬ tor to alter the angle of the optical axis so that the optical structure, comprising the lens 5 and prism 6, may lie parallel to a circuit board 9. This facilitates a relatively flat mechanical structure and permits the circuit board to support both the imaging device 8 and the optical structure 3, 5, 6 as one unit.
The reflecting properties of the prism 6 may be enhanced by silvering face 7, or by replacing this prism entirely with a mirror in the plane of the face 7. Also the optical principle of the system may be preserved if a pinhole aperture is used in place of the lens 5.
The source of the incident light may be provided by ambient light through any of the available faces of the prism 3, or by one or more artificial light sources mounted in the vicinity of the prism 3. In Figure 2 a light source 12 is used and a glass plate (or partly- silvered mirror) 11 has a surface 13 from which the light from the source 12 is fed into the prism 3.
In operation, the viewing angle set by the relation¬ ship between the device 8, the prisms 3 and 6 and the lens 5 is preferably below the critical angle causing total internal reflection at the hypotenuse face 2 of the prism 3. In this case the viewed image is normally black, except where ridges of the fingerprint make contact with the surface of the prism, causing scattered light to form a bright image in the viewing direction. A typical such image is shown at 15 in Figure 3. The light-sensitive surface of the photo-detector device 8 is divided into a multiplicity of photon-sensi¬ tive areas, each representing one pixel of the projected image 15 shown in Figure 3.
The chief attractions of the device shown in Figure 2 are that it is small and solid-state (there are no moving parts) and that it should be economical to produce in volume. All of the components (both optical and elec¬ tronic) can be mounted on a single circuit card. It senses the print of any fingertip presented by touching the face 2 of the prism 3. The capture time may be a fraction of a second. The result is a high contrast black/white image stored as a pattern of l's and 0's in a Random Access Memory or similar device.
When the print image is required in a high-contrast (black/white) form, the photo-detector device 8 should include, or be followed by, a binary discriminator to decide the value of each sample point in the image 15. This requirement may be met by using a Dynamic Random Access Memory (DRAM) device as a combined photo-detector and binary discriminator. Irrespective of end use, the production cost of a recognition system according to the invention may be reduced by using a DRAM imager/ discriminator in place of a conventional solid-state photo-detector device.
Preferably an image of the fingerprint is required in a simple binary (black and white) representation. The process of binary discrimination may occur within the photo-detector device itself by applying a threshold of decision uniformly across the received image. Alter- natively the discrimination may occur in a separate pro¬ cess whereby an analogue representation of the image is converted to a multiple-level digital form and a threshold of discrimination is derived separately for each sample point, or area of samples, according to the average values of the samples within the local neighbour¬ hood. This process is known as adaptive thresholding and serves to cancel gross variations in the intensity of the print image due to differing surface conditions and contact pressures.
An important aspect of this invention resides in - the recognition process. To achieve the aims of fast response time and low hardware cost, it is desirable that this should involve minimal computation. Existing schemes based on minutiae extraction and comparison are markedly expensive in this context. They have developed through earlier work on print matching for Police and Court applications. This degree of analysis may be un¬ warranted in a consummer application, where the error rate needs to be sufficiently low to deter a fraud attempt, but need not be so low as to offer an absolute guarantee of identity.
The preferred recognition algorithm employed is a form of "binary correlation" . In its simplest embodi- ment this involves comparing a binarised image of the print with a binary reference image, and counting the coincidences (black with black, and white with white). This is an elementary computational exercise which may be executed at high speed in electronic hardware. However, this simple form has several practical disadvantages. Firstly, where the reference is a whole print image (per¬ haps 64K bits of information), the storage requirement is undesirably large. Secondly, the print image may not be consistently aligned with the optical path of the sensing mechanism, so that both translational and rotational misalignment is possible. Thirdly, and despite the use of adaptive threshold techniques, the print image may differ marginally from trial to trial according to the lighting conditions, the pressure of contact and the condition of the skin (dry or greasy). Finally, the print may be distorted due to stretching of the skin according to the direction and force of contact.
We disclose here four novel procedures that modify the direct form of binary correlation to overcome each of the problems identified above and ensure a practically successful print recognition mechanism.
To reduce the storage and computational requirements, a reference template is derived which contains relatively few samples chosen in a fixed pattern from the print image, for the purpose of example, suppose that we use a reference template of 100 points, selected from an image of 256 x 256 pixels. Both the storage and compu¬ tation times using this template are reduced in the ratio 100:65,536 over the use of the full image. The possible combinations of a 100-bit template are nevertheless suff¬ icient to ensure a small likelihood of significant corre¬ lation, except for an identical' print."
Misalignment of the print is accommodated by the use of multiple trial correlations over a range of potential positions and orientations. For example, later¬ al movements up to 64 pixels in any direction in one pixel steps, and rotational movements up to +/- 5 degrees in one degree steps, may be examined in a set of approxi¬ mately 180,000 trials. A success in any one trial may be taken as an indication of a match at a particular position and orientation.
The extent of the misalignment, and thus the number of potential trials requiired, may be restricted by the use of a raised moulding 14 on the surface of the prism to which the finger is presented. This moulding acts as a guide to maintain the area of contact in an approx¬ imately consistent position and orientation. Marginal variations in the images obtained from the same print may still arise. These are accommodated by recoding the reference template to indicate the most likely areas of variation, and then inhibiting these samples from the correlation. The samples most frequently effected are those that lie close to the ridge/trough (white/black) transitions. These may be identified in one approach by marking as "indeterminate" any pixel which contains another pixel of the opposite colour within a chosen radius (for example, a radius of 1 or 2 pixels). Now the reference template contains a set of samples, each marked "black", "white" or "indeterminate" ("b", "w" and "?" in Figure 4b). During correlation, matches and mismatches are counted from the determinate ("b" and "w" ) samples only. These samples represent black and white regions at the cores of troughs and ridges, where the same value may consistently be expected. The final correlation score may then be taken as the ratio of this count.to the potential number of determinate candidates,
Distortion due to stretching and compression of the skin can spoil direct matching over large print areas. These forms of image distortion are accommodated by using a reference template which covers only an area of the
2 print of less than 10 mm (for example 1 or 2 mm square).
Unfortunately, the use of small template areas with many trials (as described above) may significantly in¬ crease the likelihood of a match being detected in part of a non-identical print. This reduces the discriminating power of the recognition system and is an undesirable feature. Higher levels of discrimination may be restored by using multiple templates (as shown at A and B in Figure 5a) arranged in a predetermined pattern over the image space C. Distortion by stretching may be accommodated in this process by permitting small relative displacements (both translational and rotational) of the individual templates about their expected positions (as is shown in Figure 5c).
When matching a set of templates to a print image using this process, it is not necessary to compute corre- lation scores for every possible arrangement of the tem¬ plates at every possible trial position and orientation. This would be a combinatorially excessive task. Instead, it is sufficient to compute the correlation score for one template in the first instance and to reject a trial position solely on the basis of the failure of this single template. Conversely, a high correlation score for one template may be taken as an indication of a possible match, so that arrangements of a second template may be tested. Third and subsequent templates may be tested conditionally upon the success of the preceding templates in the set, and so on. A match is indicated only by a combination of high scores for the complete set of templates.
To achieve short recognition times and low hardware cost it is desirable to execute the processes of binary correlation described above in one or more specialised large-scale integrated circuits.
Applications
Taking the above detection and matching processes, it is possible to address several applications in the field of personal identification and security.
In one application (see Figure 6), the derived refer¬ ence template(s) for an individual may be recorded onto the magnetic strip 30 on the reverse side of a cheque or credit card 31. A self-contained unit 32 at the point of sale may then be used to read this reference from the magnetic strip in a card reader 33, form a real¬ time image of the fingerprint of the person presenting the card in a print reader 34, and proceed to verify his identity as the true owner of the card in a matcher unit 35.
When the point-of-sale is networked to some central computer 36 (as in electronic funds transfer) other com¬ binations become possible; in particular the reference template may be stored in the remote computer 36, rather than on the card 31. This admits a very secure system which is proof against card (and template) forgery as well as theft. These schemes afford the option of per¬ forming the match in the central computer, with the advan¬ tage of removing matching hardware from the point-of- sale equipment, thereby reducing its cost.
"Possible embodiments of this theme include:
a) Storing the template in the central computer 36 and a pass-number on the magnetic strip 30 of the card 31 (as shown in Figure 7). On presentation of the card at the point-of-sale, a pass-number is transmitted to the central computer 36. This pass-number is used to bring forth a representative template which is then transmitted to the point-of-sale matcher unit 35 for local confirmation of identity.
b) Storing a whole print image in the central com¬ puter 36, and a pass-number on the strip 30 on the card 31. The point-of-sale equipment transmits the pass- number and a sparsely sampled image (template) set to the central computer. The computer then matches the received template against a full print reference in a remote matcher 35a and transmits confirmation back to the point-of-sale (see Figure 8).
A further variation on the above is to allow the consumer to remember the pass-number, to be keyed in at a keyboard 37 at the point-of-sale. This is shown in Figure 9 and removes the requirement for the issue and maintenance of a card system, and obviates the require¬ ment for any card reader at the point-of-sale.
The recognition system disclosed here may further be used as the basis of a secure remote computer access system. In this case the identity of a user at a remote terminal may be confirmed by providing print-sensor equip¬ ment at the terminal site capable of transmitting an image of the print, or a reduced template form of the image, to the host machine for verification.
The recognition system may further be used as the basis of a secure doorlock or site access device. In, this case a library of templates corresponding to the set of people to. be permitted entry, may be stored in the lock device, or remotely. The user may present a card containing magnetic or optically encoded identity infor¬ mation, or may enter an identity code at a keypad, which information is used to bring forth reference templates which are used to verify his identity.

Claims

1. A method of authenticating a person by comparing information from a currently taken skin-pattern with stored information from a previously taken skin-pattern characterised in that the currently taken skin-pattern is produced on a contact surface, an image of the print of the skin pattern on the contact surface is projected onto a photo-detector device, the intensity variations of the print image in at least one region thereof imping¬ ing on the photo-detector device is assessed in digital form in a multiplicity of different sub-regions of the or each said region to create a first digital signal train, a second digital signal train is derived from the stored skin pattern information and the first and second signal trains are compared to determine the degree of coincidence therebetween, an assessment of the deter¬ mined degree being used to decide whether the currently- taken and stored skin patterns are sufficiently similar ' to authenticate the person.
2. A method as claimed in claim 1, characterised in that the image of the skin pattern is created by making the contact surface, the hypotenuse face of a right angled prism and projecting an image of this pattern-contacted face onto a surface of the photo-detector device which is divided into a multiplicity of separate photon-sensi- tive areas, each representing one pixel of the projected image.
3. A method as claimed in claim 1 or claim 2, char¬ acterised in that the degree of coincidence between the first and second signal trains is assessed on the basis of direct correlation.
4. A method as claimed in claim 3, characterised in that the direct correlation is effected using, as the stored information, a reference template representing less than 10% of the full image of the currently-taken skin pattern.
5. A method as claimed in claim 4 , characterised in that only determinate samples of the image which can clearly ' be categorised as a binary "1" or a binary "0" are used for the correlation, all "indeterminate" samples being discounted.
6. A method as claimed in claim 4, characterised in that possible misalignment between currently and pre- viously taken skin patterns is allowed for by the use of multiple trial correlations over a range of stepped lateral movements and a range of discrete angular dis¬ placements of the template relative to the currently taken skin pattern.
7. A method as claimed in any of claims 4 to 6, characterised in that two or more templates are used and the direct correlation is made while allowing relative translational and/or rotational movements between the two or more templates.
8. In the operation of the method of claim 1, a finger print capture device comprising a photo-detector device having a surface divided into a matrix of separate photosensitive areas, each of which can monitor the light intensity of one pixel of an image projected thereon and means to project a finger print pattern onto said matrix-divided surface, characterised in that the finger print pattern is created on the hypotenuse face (2) of a right angle prism (3), the prism (3), an illuminating source (12) for the face (2), an optical system (5, 6, 11, 12) for projecting an image of the hypotenuse face onto the said matrix-divided surface . and the photo- detector device (8) being mounted together as a composite unit.
9. A device as claimed in claim 8, characterised in that the hypotenuse face ( 2) of the prism ( 3 ) includes means (14) to encourage consistently similar locations of fingers (1) on the hypotenuse face (2).
10. A device as claimed in claim 8 or claim 9, characterised in that the device is used to create a first signal train from a real time image of a finger print of a presenter of a sheet member required for a cash transaction and is associated with means to read from the sheet member the second signal train.
11. A device as claimed in claim 8 or claim 9, characterised in that the device is used to create a first signal train from a real time image of a finger print of a person requiring verification, the capture device being linked to a remote data bank from which the second signal trains of fingerprints of many different persons can be generated and the local capture device being associated with means whereby a nominated person's second signal train can be called-up for comparison with an output of the local capture device.
12. A device as claimed in claim 8 or 9, charac¬ terised in that it is associated with the release mechan¬ ism of a normally-locked site access device.
PCT/GB1986/000219 1985-04-22 1986-04-21 Skin-pattern recognition method and device WO1986006527A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB8510174 1985-04-22
GB8510174 1985-04-22

Publications (1)

Publication Number Publication Date
WO1986006527A1 true WO1986006527A1 (en) 1986-11-06

Family

ID=10577984

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB1986/000219 WO1986006527A1 (en) 1985-04-22 1986-04-21 Skin-pattern recognition method and device

Country Status (5)

Country Link
US (1) US4805223A (en)
EP (1) EP0218668A1 (en)
JP (1) JPS62502575A (en)
GB (1) GB2174831B (en)
WO (1) WO1986006527A1 (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0343580A2 (en) * 1988-05-24 1989-11-29 Nec Corporation Method and apparatus for matching fingerprints
DE3834046A1 (en) * 1988-10-06 1990-04-12 Karl Lambert Gohlke Method and device for limiting the access to certain data areas of a computer
DE3834048A1 (en) * 1988-10-06 1990-04-12 Karl Lambert Gohlke Method for optoelectronic identification of a person
EP0468522A2 (en) * 1990-07-27 1992-01-29 Yozan Inc. A fingerprint photographing system
FR2678821A1 (en) * 1991-07-11 1993-01-15 Macron Patrick Ralph Device for anthropometric recognition of an individual
EP0590224A2 (en) * 1992-09-29 1994-04-06 Franco Russi Improved method for making credit documents in general and device for detecting property marks thereon
WO1994025938A1 (en) * 1993-04-27 1994-11-10 Personal Biometric Encoders Limited Fingerprint sensor
WO1995002225A1 (en) * 1993-07-06 1995-01-19 Alfons Behnke Identification card
WO1996005576A1 (en) * 1994-08-10 1996-02-22 Prima Officina Carte Valori Turati Lombardi & C.S.P.A. Credit document connected to a document or customised card, independent customised credit card and associated issuance and validation equipment
WO1998052157A1 (en) * 1997-05-16 1998-11-19 Authentec, Inc. Fingerprint sensor with gain control features and associated methods
WO1999039310A1 (en) * 1998-01-30 1999-08-05 Phelps Barry C Biometric authentication system and method
US6383177B1 (en) 1997-08-29 2002-05-07 Asah Medico A/S Apparatus for tissue treatment
US6676654B1 (en) 1997-08-29 2004-01-13 Asah Medico A/S Apparatus for tissue treatment and having a monitor for display of tissue features
US6695206B2 (en) 1996-01-09 2004-02-24 Personal Biometric Encoders Ltd. Identification system displaying a user image at a remote location
EP1548637A2 (en) * 1994-08-25 2005-06-29 P-Seven Holdings Pty Ltd Method and apparatus for providing identification
WO2010122497A1 (en) * 2009-04-20 2010-10-28 Capicol (Pty) Limited A payment transaction processing and authorization system and method

Families Citing this family (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2644844B2 (en) * 1988-09-20 1997-08-25 株式会社日立製作所 Distributed image recognition system
JP2557510B2 (en) * 1988-12-29 1996-11-27 株式会社東芝 Personal authentication device
GB8918698D0 (en) * 1989-08-16 1989-09-27 Quantum Fund Limited The Skin pattern monitoring
US5146102A (en) * 1990-02-22 1992-09-08 Kabushiki Kaisha Toshiba Fingerprint image input apparatus including a cylindrical lens
JPH0424889A (en) * 1990-05-21 1992-01-28 Toshiba Corp Ic card provided with personal identification function
JP2973676B2 (en) * 1992-01-23 1999-11-08 松下電器産業株式会社 Face image feature point extraction device
EP0593386A3 (en) * 1992-10-16 1996-07-31 Ibm Method and apparatus for accessing touch screen desktop objects via fingerprint recognition
US6002787A (en) * 1992-10-27 1999-12-14 Jasper Consulting, Inc. Fingerprint analyzing and encoding system
GB2278478B (en) * 1993-05-27 1997-06-11 Eds Scicon Defence Ltd Electronic classification system
US5509083A (en) * 1994-06-15 1996-04-16 Nooral S. Abtahi Method and apparatus for confirming the identity of an individual presenting an identification card
US7631193B1 (en) 1994-11-28 2009-12-08 Yt Acquisition Corporation Tokenless identification system for authorization of electronic transactions and electronic transmissions
US6950810B2 (en) * 1994-11-28 2005-09-27 Indivos Corporation Tokenless biometric electronic financial transactions via a third party identicator
US7613659B1 (en) * 1994-11-28 2009-11-03 Yt Acquisition Corporation System and method for processing tokenless biometric electronic transmissions using an electronic rule module clearinghouse
US7882032B1 (en) 1994-11-28 2011-02-01 Open Invention Network, Llc System and method for tokenless biometric authorization of electronic communications
US7248719B2 (en) * 1994-11-28 2007-07-24 Indivos Corporation Tokenless electronic transaction system
US20040128249A1 (en) * 1994-11-28 2004-07-01 Indivos Corporation, A Delaware Corporation System and method for tokenless biometric electronic scrip
US6397198B1 (en) * 1994-11-28 2002-05-28 Indivos Corporation Tokenless biometric electronic transactions using an audio signature to identify the transaction processor
US5513272A (en) * 1994-12-05 1996-04-30 Wizards, Llc System for verifying use of a credit/identification card including recording of physical attributes of unauthorized users
US5812252A (en) * 1995-01-31 1998-09-22 Arete Associates Fingerprint--Acquisition apparatus for access control; personal weapon and other systems controlled thereby
US5815252A (en) * 1995-09-05 1998-09-29 Canon Kabushiki Kaisha Biometric identification process and system utilizing multiple parameters scans for reduction of false negatives
GB2309110B (en) * 1996-01-09 1999-12-08 Personal Biometric Encoders Identification system
GB2309329A (en) * 1996-01-18 1997-07-23 John Gerald Bullard Fingerprint recognition
US5956415A (en) * 1996-01-26 1999-09-21 Harris Corporation Enhanced security fingerprint sensor package and related methods
US5796858A (en) * 1996-05-10 1998-08-18 Digital Persona, Inc. Fingerprint sensing system using a sheet prism
WO2004097740A1 (en) * 1996-08-26 2004-11-11 Masahiko Yamaguchi Method of updating dictionary images in fingerprint recognition apparatus
US5878155A (en) * 1996-09-05 1999-03-02 Heeter; Thomas W. Method for verifying human identity during electronic sale transactions
GB9621647D0 (en) * 1996-10-17 1996-12-11 Jones David J Personal guardcard
US5982913A (en) * 1997-03-25 1999-11-09 The United States Of America As Represented By The National Security Agency Method of verification using a subset of claimant's fingerprint
US6356649B2 (en) * 1997-04-11 2002-03-12 Arete Associate, Inc. “Systems and methods with identity verification by streamlined comparison and interpretation of fingerprints and the like”
US6125192A (en) * 1997-04-21 2000-09-26 Digital Persona, Inc. Fingerprint recognition system
US5838820A (en) * 1997-04-30 1998-11-17 Bergman; Anthony J. Pattern recognition apparatus and method
US6018739A (en) * 1997-05-15 2000-01-25 Raytheon Company Biometric personnel identification system
US6098330A (en) * 1997-05-16 2000-08-08 Authentec, Inc. Machine including vibration and shock resistant fingerprint sensor and related methods
US5982914A (en) * 1997-07-29 1999-11-09 Smarttouch, Inc. Identification of individuals from association of finger pores and macrofeatures
US6038332A (en) * 1997-09-05 2000-03-14 Digital Biometrics, Inc. Method and apparatus for capturing the image of a palm
US5959541A (en) * 1997-09-23 1999-09-28 Accu-Time Systems, Inc. Biometric time and attendance system with epidermal topographical updating capability
US6320974B1 (en) 1997-09-25 2001-11-20 Raytheon Company Stand-alone biometric identification system
US6317544B1 (en) * 1997-09-25 2001-11-13 Raytheon Company Distributed mobile biometric identification system with a centralized server and mobile workstations
DE19743602A1 (en) * 1997-10-02 1999-04-08 Marquardt Gmbh Electronic lock for a locking system using electronic ignition key for car
US6035398A (en) * 1997-11-14 2000-03-07 Digitalpersona, Inc. Cryptographic key generation using biometric data
US6122737A (en) * 1997-11-14 2000-09-19 Digital Persona, Inc. Method for using fingerprints to distribute information over a network
DE69815272T3 (en) * 1997-12-22 2007-12-27 Northrop Grumman Corp. (N.D.Ges.D.Staates Delaware), Los Angeles Fingerprint comparison controlled access to doors and machines
US6980670B1 (en) * 1998-02-09 2005-12-27 Indivos Corporation Biometric tokenless electronic rewards system and method
US6324310B1 (en) 1998-06-02 2001-11-27 Digital Persona, Inc. Method and apparatus for scanning a fingerprint using a linear sensor
US6188781B1 (en) 1998-07-28 2001-02-13 Digital Persona, Inc. Method and apparatus for illuminating a fingerprint through side illumination of a platen
US6950539B2 (en) * 1998-09-16 2005-09-27 Digital Persona Configurable multi-function touchpad device
US6396599B1 (en) * 1998-12-21 2002-05-28 Eastman Kodak Company Method and apparatus for modifying a portion of an image in accordance with colorimetric parameters
US6671392B1 (en) * 1998-12-25 2003-12-30 Nippon Telegraph And Telephone Corporation Fingerprint recognition apparatus and data processing method
US6097035A (en) * 1999-02-22 2000-08-01 Digital Persona, Inc. Fingerprint detection apparatus with partial fingerprint images
US6546122B1 (en) * 1999-07-29 2003-04-08 Veridicom, Inc. Method for combining fingerprint templates representing various sensed areas of a fingerprint to derive one fingerprint template representing the fingerprint
US6912300B1 (en) * 1999-08-20 2005-06-28 Mitsubishi Denki Kabushiki Kaisha Irregular pattern reader
GB2362743A (en) * 2000-05-23 2001-11-28 John Ward Inhibiting fraudulent transactions
US9165323B1 (en) 2000-05-31 2015-10-20 Open Innovation Network, LLC Biometric transaction system and method
WO2001093167A1 (en) 2000-05-31 2001-12-06 Indivos Corporation Biometric financial transaction system and method
US6867683B2 (en) * 2000-12-28 2005-03-15 Unisys Corporation High security identification system for entry to multiple zones
EP1304659A1 (en) * 2001-10-22 2003-04-23 Koninklijke KPN N.V. Method and system and monitoring apparatus for access control of persons
GB2382207A (en) * 2001-11-19 2003-05-21 Muhammad Alhamdani Fingerprint recognition
GB0128430D0 (en) * 2001-11-28 2002-01-16 Ncr Int Inc Media dispensing
US20040052403A1 (en) * 2002-01-25 2004-03-18 Houvener Robert C. High volume mobile identity verification system and method
US6757408B2 (en) * 2002-01-25 2004-06-29 Robert C. Houvener Quality assurance and training system for high volume mobile identity verification system and method
SE524727C2 (en) * 2002-05-07 2004-09-21 Precise Biometrics Ab Generation of frequency codes in conjunction with transformation and compression of fingerprint data
US20040057606A1 (en) * 2002-09-25 2004-03-25 The Hong Kong Polytechnic University Apparatus for capturing a palmprint image
US7496214B2 (en) * 2002-09-25 2009-02-24 The Hong Kong Polytechnic University Method of palm print identification
US7466846B2 (en) * 2002-09-25 2008-12-16 The Hong Kong Polytechnic University Method for analyzing a palm print for the identification of an individual using gabor analysis
CN1331099C (en) * 2004-04-23 2007-08-08 中国科学院自动化研究所 Content based image recognition method
US20050281438A1 (en) * 2004-06-21 2005-12-22 Zhang David D Palm print identification using palm line orientation
GB2429097B (en) * 2005-07-27 2008-10-29 Ingenia Technology Ltd Verification
JP2009503976A (en) * 2005-07-27 2009-01-29 インゲニア・テクノロジー・リミテッド Verification of article signatures generated from signals obtained from the scattering of coherent light radiation from the surface of the article
US20090254464A1 (en) * 2008-04-02 2009-10-08 Timetrak Systems, Inc. Time and attendance system and method
US8483448B2 (en) * 2009-11-17 2013-07-09 Scanable, Inc. Electronic sales method

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3200701A (en) * 1962-01-29 1965-08-17 Ling Temco Vought Inc Method for optical comparison of skin friction-ridge patterns
US3292149A (en) * 1964-06-18 1966-12-13 Ibm Identification and comparison apparatus for contour patterns such as fingerprints
US3581282A (en) * 1968-12-03 1971-05-25 Norman G Altman Palm print identification system
FR2262834B1 (en) * 1973-04-09 1977-10-21 Calspan Corp
US3975711A (en) * 1974-08-30 1976-08-17 Sperry Rand Corporation Real time fingerprint recording terminal
US3944978A (en) * 1974-09-09 1976-03-16 Recognition Systems, Inc. Electro-optical method and apparatus for making identifications
US4210899A (en) * 1975-06-23 1980-07-01 Fingermatrix, Inc. Fingerprint-based access control and identification apparatus
FR2315250A1 (en) * 1975-06-23 1977-01-21 Calspan Corp FINGERPRINT IDENTIFICATION SYSTEM
GB1509095A (en) * 1975-09-02 1978-04-26 Sperry Rand Corp Pattern inspection apparatus
US4032889A (en) * 1976-05-21 1977-06-28 International Business Machines Corporation Palm print identification
US4151512A (en) * 1976-09-10 1979-04-24 Rockwell International Corporation Automatic pattern processing system
US4135147A (en) * 1976-09-10 1979-01-16 Rockwell International Corporation Minutiae pattern matcher
US4186378A (en) * 1977-07-21 1980-01-29 Palmguard Inc. Identification system
US4322163A (en) * 1977-10-25 1982-03-30 Fingermatrix Inc. Finger identification
US4246568A (en) * 1978-12-08 1981-01-20 Peterson Vernon L Apparatus and method of personal identification by fingerprint comparison
JPS6012674B2 (en) * 1979-04-02 1985-04-02 日本電気株式会社 Pattern feature extraction device
DE3072034D1 (en) * 1979-12-24 1987-10-29 Electro Optic Dev Method and device for carrying out a comparison between certain patterns, especially finger prints
US4371865A (en) * 1980-07-03 1983-02-01 Palmguard, Inc. Method for analyzing stored image details
US4468809A (en) * 1981-12-23 1984-08-28 Ncr Corporation Multiple font OCR reader
ZA832075B (en) * 1982-03-26 1983-12-28 Fingermatrix Inc Fingerprint identification system
US4581760A (en) * 1983-04-27 1986-04-08 Fingermatrix, Inc. Fingerprint verification method
US4641350A (en) * 1984-05-17 1987-02-03 Bunn Robert F Fingerprint identification system
DE3577485D1 (en) * 1984-07-18 1990-06-07 Nec Corp IMAGE INPUT DEVICE FOR PROCESSING A FINGERPRINT BEFORE IDENTIFICATION.
US4618988A (en) * 1984-07-25 1986-10-21 Fingermatrix, Inc. Matcher

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
IBM Technical Disclosure Bulletin, Vol. 17, No. 12, May 1975 (New York, US) C. WEST et al.: 'Fingerprint Based Person Verification System', pages 3741-3743, see page 3741, line 1 - page 3743, line 13; figures *

Cited By (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0343580A3 (en) * 1988-05-24 1990-03-21 Nec Corporation Method and apparatus for matching fingerprints
EP0343580A2 (en) * 1988-05-24 1989-11-29 Nec Corporation Method and apparatus for matching fingerprints
DE3834046A1 (en) * 1988-10-06 1990-04-12 Karl Lambert Gohlke Method and device for limiting the access to certain data areas of a computer
DE3834048A1 (en) * 1988-10-06 1990-04-12 Karl Lambert Gohlke Method for optoelectronic identification of a person
EP0468522A2 (en) * 1990-07-27 1992-01-29 Yozan Inc. A fingerprint photographing system
EP0468522A3 (en) * 1990-07-27 1993-01-13 Ezel Inc. A fingerprint photographing system
FR2678821A1 (en) * 1991-07-11 1993-01-15 Macron Patrick Ralph Device for anthropometric recognition of an individual
EP0590224A3 (en) * 1992-09-29 1995-03-08 Franco Russi Improved method for making credit documents in general and device for detecting property marks thereon.
EP0590224A2 (en) * 1992-09-29 1994-04-06 Franco Russi Improved method for making credit documents in general and device for detecting property marks thereon
WO1994025938A1 (en) * 1993-04-27 1994-11-10 Personal Biometric Encoders Limited Fingerprint sensor
US5825005A (en) * 1993-07-06 1998-10-20 Behnke; Alfons Method of encoding identification cards and verifying such encoded identification cards, and apparatus for carrying out such a method
WO1995002225A1 (en) * 1993-07-06 1995-01-19 Alfons Behnke Identification card
WO1996005576A1 (en) * 1994-08-10 1996-02-22 Prima Officina Carte Valori Turati Lombardi & C.S.P.A. Credit document connected to a document or customised card, independent customised credit card and associated issuance and validation equipment
US6010068A (en) * 1994-08-10 2000-01-04 Nadir Technology Company Limited Credit document connected to a document or customized card, independent customized credit card and associated issuance and validation equipment
US8009873B2 (en) 1994-08-25 2011-08-30 Neotec Holdings Limited Method and apparatus for providing identification
EP1548637A3 (en) * 1994-08-25 2008-01-02 Neotec Holdings Limited Method and apparatus for providing identification
EP1548637A2 (en) * 1994-08-25 2005-06-29 P-Seven Holdings Pty Ltd Method and apparatus for providing identification
US6695206B2 (en) 1996-01-09 2004-02-24 Personal Biometric Encoders Ltd. Identification system displaying a user image at a remote location
WO1998052157A1 (en) * 1997-05-16 1998-11-19 Authentec, Inc. Fingerprint sensor with gain control features and associated methods
US6259804B1 (en) 1997-05-16 2001-07-10 Authentic, Inc. Fingerprint sensor with gain control features and associated methods
USRE38670E1 (en) 1997-08-29 2004-12-14 Asah Medico A/S Apparatus for tissue treatment
US6676654B1 (en) 1997-08-29 2004-01-13 Asah Medico A/S Apparatus for tissue treatment and having a monitor for display of tissue features
US6383177B1 (en) 1997-08-29 2002-05-07 Asah Medico A/S Apparatus for tissue treatment
WO1999039310A1 (en) * 1998-01-30 1999-08-05 Phelps Barry C Biometric authentication system and method
WO2010122497A1 (en) * 2009-04-20 2010-10-28 Capicol (Pty) Limited A payment transaction processing and authorization system and method

Also Published As

Publication number Publication date
GB2174831A (en) 1986-11-12
US4805223A (en) 1989-02-14
JPS62502575A (en) 1987-10-01
GB2174831B (en) 1988-12-14
GB8609673D0 (en) 1986-05-29
EP0218668A1 (en) 1987-04-22

Similar Documents

Publication Publication Date Title
US4805223A (en) Skin-pattern recognition method and device
US4896363A (en) Apparatus and method for matching image characteristics such as fingerprint minutiae
CA2256672C (en) Biometric recognition using a classification neural network
EP0310603B1 (en) Method and apparatus for verifying identity
US5869822A (en) Automated fingerprint identification system
US5815252A (en) Biometric identification process and system utilizing multiple parameters scans for reduction of false negatives
Jain et al. Introduction to biometrics
US5073950A (en) Finger profile identification system
US6980669B1 (en) User authentication apparatus which uses biometrics and user authentication method for use with user authentication apparatus
US5594806A (en) Knuckle profile indentity verification system
EP0159037B1 (en) Identification system employing verification of fingerprints
Joshi et al. Computer-vision-based approach to personal identification using finger crease pattern
US20220300593A1 (en) System and method of biometric identification of a subject
EP1251448B1 (en) Method, device and system for biometric identification
CA2142227A1 (en) Combination radiofrequency identification card - fingerprint identification system
WO2009028926A2 (en) Apparatus and method for volumetric multi-modal hand biometrlc identification
EP0300167A2 (en) Apparatus and method for matching image characteristics such as fingerprint minutiae
JP2000048194A (en) Device for recognizing fingerprint and palmprint
JP2010009377A (en) Verification system, verification method, program and storage medium
JP2634656B2 (en) Fingerprint image reader
KR20230155661A (en) Electronic voting method using the biometric recognition type in on-off line
Ground Fingerprints: Proving Ground for Pattern Recognition
Afolabi et al. Securing E-Library System with Bimodal Biometric
GB2278478A (en) Fingerprint classification system
IE61352B1 (en) Method and apparatus for verifying identity

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): JP US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH DE FR GB IT LU NL SE

WWE Wipo information: entry into national phase

Ref document number: 1986902459

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 1986902459

Country of ref document: EP

WWW Wipo information: withdrawn in national office

Ref document number: 1986902459

Country of ref document: EP