WO1993003348A1 - Sample evaluation - Google Patents
Sample evaluation Download PDFInfo
- Publication number
- WO1993003348A1 WO1993003348A1 PCT/GB1992/001375 GB9201375W WO9303348A1 WO 1993003348 A1 WO1993003348 A1 WO 1993003348A1 GB 9201375 W GB9201375 W GB 9201375W WO 9303348 A1 WO9303348 A1 WO 9303348A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sample
- neural network
- filtering
- spectrum
- output
- Prior art date
Links
- 238000011156 evaluation Methods 0.000 title description 2
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000001228 spectrum Methods 0.000 claims abstract description 15
- 230000005855 radiation Effects 0.000 claims abstract description 13
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 230000006978 adaptation Effects 0.000 claims abstract description 6
- 230000003287 optical effect Effects 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 2
- 238000000034 method Methods 0.000 description 4
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 229910052710 silicon Inorganic materials 0.000 description 3
- 239000010703 silicon Substances 0.000 description 3
- 238000010304 firing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 239000010784 textile waste Substances 0.000 description 1
- 238000001429 visible spectrum Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
- G01J3/51—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors using colour filters
- G01J3/513—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors using colour filters having fixed filter-detector pairs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Definitions
- This invention relates to methods and apparatus for evaluating samples, more particularly to evaluating the colour of samples or some property of samples that can be investigated using reflected or other radiation from the samples.
- Standard colourimeters are based on spectrophoto- metric techniques and are inherently expensive. Their size and sampling rate preclude many application areas including on-line measurement.
- the present invention provides a fast acting, low cost colour measurement system and, more generally, a system for evaluating a sample using radiation from the sample.
- the invention comprises a system for evaluating a sample in which radiation from the sample is partitioned by filtering to a plurality of sensors connected as inputs to a neural network which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
- the neural network may be capable of adaptation by repeated exposure of the system to a particular radiation spectrum and adjustment of the neural network more closely to approximate the output to the particular representation of the particular spectrum.
- the colour of the sample may be evaluated, the filtering being in the optical spectrum.
- the infra red which may be used to evaluate the material of the sample, particularly to distinguish between different polymers used for example in the plastics and textiles industries.
- the output format may correspond to red, blue and green coordinates of a colour coordinate system.
- the evaluating system may be "taught" to recognize colours by comparing its output with that of a standard spectrophotometric colourimeter and adjusting the neural network until the outputs correspond.
- assisted learning Such a procedure is referred to as assisted learning and would be appropriate where the system was required to yield absolute values; an unassisted learning procedure could be used for other purposes, for example where a collection of articles was required to be sorted into piles according to the material from which the articles were made, without any prior knowledge of what or how many different materials were involved.
- a neural network as contemplated herein may be implemented in software or hardware and comprise input and output elements interconnected by a network of elements which in a typical hardware implementation will be transistors with variable firing threshold levels and in software implementation will be algorithms.
- Figure 1 is a schematic representation of one system
- FIG 2 is a diagram showing the bands passed by the filters of the system of Figure 1;
- Figure 3 is a schematic representation of another system;
- FIG. 4 is an illustration of filterless spectrum partitioning
- Figure 5 is a diagrammatic view of the system of Figure 1 in operation dividing textile waste into different colour bins.
- the drawings illustrate systems for evaluating samples 11 in which radiation from the sample 11 - usually, of course, reflected radiation from an illuminating source such as a lamp - is partitioned as by filtering to a plurality of sensors 12 connected to inputs 13 of a neural network 14 which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
- an illuminating source such as a lamp -
- a neural network 14 which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
- Figure 1 illustrates a system for evaluating the colour of the sample 11 - which might be a piece of waste fabric, for example, which it is desired to assign to a particular bin 41 by a system as illustrated in Figure 5 in which samples 11 are viewed by a unit 40 incorporating the system and pushed off a conveyor belt 42 which carries them past the unit 40 which actuates pushers 43 consigning so selected articles to the appropriate bin 41 according to their colour.
- a standard spectrophotometric colour analyser could do this but at a slow rate, because of the processing time required to evaluate any particular colour, besides which such instruments are expensive and for other reasons difficult to incorporate into an on-line measurement system.
- the present system is capable of very fast action and is moreover relatively inexpensive.
- An infra-red filter F_ R is provided to filter out infra-red which affects silicon photodiodes.
- the current output of the photodiodes 12 is converted to a voltage output which is digitised in A/D converters 15. For simplicity there are shown four outputs from each A/D converter 15, though in practice sixteen bit resolution would be provided.
- the neural network 14 is shown as having output elements 16 connected via intermediate elements 17 with a connection architecture which is merely suggested by links 18, the links having adjustable "weights” and the intermediate and output elements 17, 16 having thresholds for "firing" or switching which are also adjustable according to inherent properties of the network.
- each output may have a separate connection for each bit of information exactly as the input arrangement.
- the outputs 16 are connected to a display arrangement 21 which has the format of any desired representation of colour such as a colour triangle which has red, blue and green coordinates and which may be the same as the display arrangement 22 of a conventional spectrophotometric colourimeter 23.
- the silicon photodiodes 12 are selected to be inexpensive and hence not necessarily precision devices.
- the filters F are arbitarily chosen except, of course, that filter F R should pass predominantly red light, F patron blue light and F G green light. It is however desirable (though probably quite difficult not to achieve with inexpensive filters) that the filters collectively pass all frequencies of the visible spectrum to a greater or lesser extent, which is to say their pass bands overlap, as shown in Figure 2. If there is a part of the red that is not overlapped it is desirable it be left of the peak P R as shown in Figure 2 and, for blue right, respectively, of the peak P_.
- the network may be adapted to give an output corresponding to the output of the conventional colouri eter 23.
- the outputs from the two displays " are compared in a processor 24 which signals to the network 14 that it should or should not adapt by changing the weights and thresholds either in a predetermined manner or according to the value of an activation function which depends on the degree by which the network output is in error as compared to the colourimeter output.
- Figure 4 illustrates how colour filters may be dispensed with by selecting photodiodes with different frequency responses - the curves indicate hypothetical photodiodes with frequency response curves F. , F « and F,.
- Figure 3 finally, shows a system using infra red filters 31 passing infra red in two overlapping frequency ranges to infra red sensors 32 inputting through analogue-to-digital converters 33 and a mutliplexer 34 into a microcomputer 35 arranged to operate as a neural network by having the inputs converted to outputs according to algorithms with variable parameters.
- a program could be arranged to detect groupings of outputs and then to adapt the network by adjusting the parameter to show up the groupings, so that the items from which the inputs are derived can be assigned into different classes of materials as identified by their IR spectra.
Abstract
There is disclosed a system for evaluating a sample in which radiation from the sample is partitioned by filtering to a plurality of sensors connected as inputs to a neural network which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
Description
SAMPLE EVALUATION
This invention relates to methods and apparatus for evaluating samples, more particularly to evaluating the colour of samples or some property of samples that can be investigated using reflected or other radiation from the samples.
Standard colourimeters are based on spectrophoto- metric techniques and are inherently expensive. Their size and sampling rate preclude many application areas including on-line measurement.
The present invention provides a fast acting, low cost colour measurement system and, more generally, a system for evaluating a sample using radiation from the sample.
The invention comprises a system for evaluating a sample in which radiation from the sample is partitioned by filtering to a plurality of sensors connected as inputs to a neural network which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
The neural network may be capable of adaptation by repeated exposure of the system to a particular
radiation spectrum and adjustment of the neural network more closely to approximate the output to the particular representation of the particular spectrum.
The colour of the sample may be evaluated, the filtering being in the optical spectrum. There may be three filters corresponding to red, blue and green, and the filtering may collectively pass the entire optical spectrum. There may, of course, be more filters each with an associated sensor, which will permit of greater discrimination. Or, for some special purposes, it may be sufficient to have fewer filters and sensors - two filters and sensors, for example, or even a single filter and sensor combination and a sensor without a filter.
Other parts of the electromagnetic spectrum may be used, for example the infra red, which may be used to evaluate the material of the sample, particularly to distinguish between different polymers used for example in the plastics and textiles industries.
Where the optical spectrum is used, the output format may correspond to red, blue and green coordinates of a colour coordinate system. The evaluating system may be "taught" to recognize colours by comparing its output with that of a standard spectrophotometric
colourimeter and adjusting the neural network until the outputs correspond. Such a procedure is referred to as assisted learning and would be appropriate where the system was required to yield absolute values; an unassisted learning procedure could be used for other purposes, for example where a collection of articles was required to be sorted into piles according to the material from which the articles were made, without any prior knowledge of what or how many different materials were involved.
A neural network as contemplated herein may be implemented in software or hardware and comprise input and output elements interconnected by a network of elements which in a typical hardware implementation will be transistors with variable firing threshold levels and in software implementation will be algorithms.
Embodiments of systems for evaluating samples according to the invention will now be described with reference to the accompanying drawings, in which :-
Figure 1 is a schematic representation of one system;
Figure 2 is a diagram showing the bands passed by the filters of the system of Figure 1;
Figure 3 is a schematic representation of another system;
Figure 4 is an illustration of filterless spectrum partitioning;
and Figure 5 is a diagrammatic view of the system of Figure 1 in operation dividing textile waste into different colour bins.
The drawings illustrate systems for evaluating samples 11 in which radiation from the sample 11 - usually, of course, reflected radiation from an illuminating source such as a lamp - is partitioned as by filtering to a plurality of sensors 12 connected to inputs 13 of a neural network 14 which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
Figure 1 illustrates a system for evaluating the colour of the sample 11 - which might be a piece of waste fabric, for example, which it is desired to assign to a particular bin 41 by a system as illustrated in Figure 5 in which samples 11 are viewed by a unit 40 incorporating the system and pushed off a conveyor belt
42 which carries them past the unit 40 which actuates pushers 43 consigning so selected articles to the appropriate bin 41 according to their colour.
A standard spectrophotometric colour analyser could do this but at a slow rate, because of the processing time required to evaluate any particular colour, besides which such instruments are expensive and for other reasons difficult to incorporate into an on-line measurement system. The present system, however, is capable of very fast action and is moreover relatively inexpensive.
The sensors 12, which are for example silicon photodiodes, are covered by red, blue and green filters, FR, F_ and FG. An infra-red filter F_R is provided to filter out infra-red which affects silicon photodiodes.
The current output of the photodiodes 12 is converted to a voltage output which is digitised in A/D converters 15. For simplicity there are shown four outputs from each A/D converter 15, though in practice sixteen bit resolution would be provided.
The neural network 14 is shown as having output elements 16 connected via intermediate elements 17 with
a connection architecture which is merely suggested by links 18, the links having adjustable "weights" and the intermediate and output elements 17, 16 having thresholds for "firing" or switching which are also adjustable according to inherent properties of the network.
Three outputs 16 are shown in Figure 1 though it will be understood that each output may have a separate connection for each bit of information exactly as the input arrangement. The outputs 16 are connected to a display arrangement 21 which has the format of any desired representation of colour such as a colour triangle which has red, blue and green coordinates and which may be the same as the display arrangement 22 of a conventional spectrophotometric colourimeter 23.
The silicon photodiodes 12 are selected to be inexpensive and hence not necessarily precision devices. The filters F are arbitarily chosen except, of course, that filter FR should pass predominantly red light, F„ blue light and FG green light. It is however desirable (though probably quite difficult not to achieve with inexpensive filters) that the filters collectively pass all frequencies of the visible spectrum to a greater or lesser extent, which is to say their pass bands overlap, as shown in Figure 2. If
there is a part of the red that is not overlapped it is desirable it be left of the peak PR as shown in Figure 2 and, for blue right, respectively, of the peak P_.
Because of the imprecision of the components of the optical system, such an arrangement could not be expected to give any reliable indication of the make-up of the colour of the article 11 simply from the information contained in the current or voltage readouts from the sensors 12. However, with the possibility of adapting the weightings of the links and the threshold values of the intermediate and output elements of the neural network 14, the network may be adapted to give an output corresponding to the output of the conventional colouri eter 23.
The outputs from the two displays "are compared in a processor 24 which signals to the network 14 that it should or should not adapt by changing the weights and thresholds either in a predetermined manner or according to the value of an activation function which depends on the degree by which the network output is in error as compared to the colourimeter output.
The adjustment proceedings stepwise until the match is within predetermined limits, when "teaching" can be terminated and the conventional colourimeter discarded.
Figure 4 illustrates how colour filters may be dispensed with by selecting photodiodes with different frequency responses - the curves indicate hypothetical photodiodes with frequency response curves F. , F« and F,.
Figure 3, finally, shows a system using infra red filters 31 passing infra red in two overlapping frequency ranges to infra red sensors 32 inputting through analogue-to-digital converters 33 and a mutliplexer 34 into a microcomputer 35 arranged to operate as a neural network by having the inputs converted to outputs according to algorithms with variable parameters. A program could be arranged to detect groupings of outputs and then to adapt the network by adjusting the parameter to show up the groupings, so that the items from which the inputs are derived can be assigned into different classes of materials as identified by their IR spectra.
Claims
1. A system for evaluating a sample in which radiation from the sample is partitioned by filtering to a plurality of sensors connected as inputs to a neural network which is so configured and arranged as to have an output format corresponding to a particular representation of a radiation spectrum and which is capable of adaptation.
2. A system according to claim 1, in which the neural network is capable of adaptation by repeated exposure of the system to a particular radiation spectrum and adjustment of the neural network more closely to approximate the output to the particular representation of the particular spectrum.
3. A system according to claim 1 or claim 2, in which the colour of the sample is evaluated, the filtering being in the optical spectrum.
4. A system according to claim 3, in which there are three filters corresponding to red, blue and green.
5. A system according to claim 3 or claim 4, in which the filtering collectively passes the entire optical spectrum.
6. A system according to any one of claims 1 to 5, in which the output format corresponds to red, blue and green coordinates of a colour coordinate system.
7. A system according to any one of claims 1 to 6, in which the system is "taught" to recognise colours by comparing its output with that of a standard colouri¬ meter and adjusting the neural network until the outputs correspond.
8. A system according to claim 1, in which the material of the sample is evaluated, the filtering being in the infra red region.
9. A system according to any one of claims 1 to 8, in which the sensors are connected to the neural network through analogue to digital converters.
10. A sample sorting system including a sample evaluating system according to any one of claims 1 to 8, evaluating samples and actuating a sorting mechanism.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB9116562.1 | 1991-08-01 | ||
GB919116562A GB9116562D0 (en) | 1991-08-01 | 1991-08-01 | Sample evaluation |
Publications (1)
Publication Number | Publication Date |
---|---|
WO1993003348A1 true WO1993003348A1 (en) | 1993-02-18 |
Family
ID=10699302
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/GB1992/001375 WO1993003348A1 (en) | 1991-08-01 | 1992-07-24 | Sample evaluation |
Country Status (3)
Country | Link |
---|---|
AU (1) | AU2361992A (en) |
GB (1) | GB9116562D0 (en) |
WO (1) | WO1993003348A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0823090A1 (en) * | 1995-04-27 | 1998-02-11 | Northrop Grumman Corporation | Adaptive filtering neural network classifier |
WO1999004291A1 (en) * | 1997-07-15 | 1999-01-28 | Gsf - Forschungszentrum Für Umwelt Und Gesundheit, Gmbh | Method for detecting photon spectra |
US6383735B1 (en) | 1996-08-07 | 2002-05-07 | Forschungszentrum Karlsruhe Gmbh | Fibromyoma or carcinoma corporis uteri |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4965725A (en) * | 1988-04-08 | 1990-10-23 | Nueromedical Systems, Inc. | Neural network based automated cytological specimen classification system and method |
US4979124A (en) * | 1988-10-05 | 1990-12-18 | Cornell Research Foundation | Adaptive, neural-based signal processor |
GB2247312A (en) * | 1990-07-16 | 1992-02-26 | Univ Brunel | Surface Inspection |
-
1991
- 1991-08-01 GB GB919116562A patent/GB9116562D0/en active Pending
-
1992
- 1992-07-24 AU AU23619/92A patent/AU2361992A/en not_active Abandoned
- 1992-07-24 WO PCT/GB1992/001375 patent/WO1993003348A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4965725A (en) * | 1988-04-08 | 1990-10-23 | Nueromedical Systems, Inc. | Neural network based automated cytological specimen classification system and method |
US4965725B1 (en) * | 1988-04-08 | 1996-05-07 | Neuromedical Systems Inc | Neural network based automated cytological specimen classification system and method |
US4979124A (en) * | 1988-10-05 | 1990-12-18 | Cornell Research Foundation | Adaptive, neural-based signal processor |
GB2247312A (en) * | 1990-07-16 | 1992-02-26 | Univ Brunel | Surface Inspection |
Non-Patent Citations (1)
Title |
---|
Journal of the Society of dyers and colourists, Vol. 107, 1991 S Westland, J M Bishop, M J Bushnell and A L Ushert: "An intelligent approach to colour recipe prediction ", * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0823090A1 (en) * | 1995-04-27 | 1998-02-11 | Northrop Grumman Corporation | Adaptive filtering neural network classifier |
EP0823090A4 (en) * | 1995-04-27 | 1999-12-22 | Northrop Grumman Corp | Adaptive filtering neural network classifier |
US6383735B1 (en) | 1996-08-07 | 2002-05-07 | Forschungszentrum Karlsruhe Gmbh | Fibromyoma or carcinoma corporis uteri |
WO1999004291A1 (en) * | 1997-07-15 | 1999-01-28 | Gsf - Forschungszentrum Für Umwelt Und Gesundheit, Gmbh | Method for detecting photon spectra |
Also Published As
Publication number | Publication date |
---|---|
GB9116562D0 (en) | 1991-09-18 |
AU2361992A (en) | 1993-03-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US4057146A (en) | Optical sorting apparatus | |
US5333739A (en) | Method and apparatus for sorting bulk material | |
US6137074A (en) | Optical glass sorting machine and method | |
US5134291A (en) | Method for sorting used plastic containers and the like | |
US3060790A (en) | Colorimeter and color sorting apparatus | |
DE2431010C3 (en) | Device for the detection of foreign bodies and / or cracks in transparent containers | |
AU2002319986B2 (en) | A method of sorting objects comprising organic material | |
JPS6236170B2 (en) | ||
DE4305006A1 (en) | Automatic handling, sorting and sepn. of waste material - preliminarily sorts by size, density or volume and secondarily identifies by spectrographic analysis, for reclaiming recyclable items | |
US6433338B1 (en) | Method and device for identification of a type of material in an object and utilization therefor | |
HU181010B (en) | Method and apparatus for selecting foreign body on conveyor or from similarly moved material | |
CA2251660A1 (en) | Method and apparatus for detecting liquid presence on a reflecting surface using modulated light | |
CN101228435B (en) | Detecting and categorizing of foreign substances in a strand-like textile material | |
AU2002319986A1 (en) | A method of sorting objects comprising organic material | |
US2933613A (en) | Method and apparatus for sorting objects according to color | |
EP0208214A2 (en) | A metal detector | |
EP1101099B1 (en) | Fiber color grading system | |
US4690284A (en) | Method of and apparatus for inspecting objects using multiple position detectors | |
US5158181A (en) | Optical sorter | |
Friedrich et al. | Qualitative analysis of post-consumer and post-industrial waste via near-infrared, visual and induction identification with experimental sensor-based sorting setup | |
WO1993003348A1 (en) | Sample evaluation | |
US5448363A (en) | Food sorting by reflection of periodically scanned laser beam | |
DE19601597A1 (en) | Sorting machine using opposing detectors | |
US4105123A (en) | Fruit sorting circuitry | |
CN100361164C (en) | Double sheet detector for automated transaction machine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AT AU BB BG BR CA CH CS DE DK ES FI GB HU JP KP KR LK LU MG MN MW NL NO PL RO RU SD SE US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE CH DE DK ES FR GB GR IT LU MC NL SE BF BJ CF CG CI CM GA GN ML MR SN TD TG |
|
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
REG | Reference to national code |
Ref country code: DE Ref legal event code: 8642 |
|
NENP | Non-entry into the national phase |
Ref country code: CA |
|
122 | Ep: pct application non-entry in european phase |