EP2795592A1 - Procédé et dispositif pour déterminer des paramètres de classement pour le classement de billets de banque - Google Patents

Procédé et dispositif pour déterminer des paramètres de classement pour le classement de billets de banque

Info

Publication number
EP2795592A1
EP2795592A1 EP12813766.8A EP12813766A EP2795592A1 EP 2795592 A1 EP2795592 A1 EP 2795592A1 EP 12813766 A EP12813766 A EP 12813766A EP 2795592 A1 EP2795592 A1 EP 2795592A1
Authority
EP
European Patent Office
Prior art keywords
banknotes
determined
sensor unit
reference banknotes
measurement data
Prior art date
Legal status (The legal status 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 status listed.)
Withdrawn
Application number
EP12813766.8A
Other languages
German (de)
English (en)
Inventor
Matthias Hecht
Stefan Kokrhoun
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Giesecke and Devrient Currency Technology GmbH
Original Assignee
Giesecke and Devrient GmbH
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 Giesecke and Devrient GmbH filed Critical Giesecke and Devrient GmbH
Publication of EP2795592A1 publication Critical patent/EP2795592A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
    • G07D11/50—Sorting or counting valuable papers
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/06—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency using wave or particle radiation
    • G07D7/08—Acoustic waves
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/06—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency using wave or particle radiation
    • G07D7/12—Visible light, infrared or ultraviolet radiation

Definitions

  • the invention relates to a method for the determination of classification parameters or adaptation parameters for the classification of banknotes, in which properties of a banknote to be classified are determined and based on the determined properties of the banknote by means of the classification parameters a class of several possible classes be - is true.
  • the invention further relates to a device for carrying out the method, a computer program for carrying out the method and a data carrier with the computer program.
  • banknotes Although the present invention is in principle applicable without restriction to any type of sheet-like value documents, a particular focus of the present invention is on banknotes, so that in the following, for the sake of simplicity, the term “banknotes” is generally used instead of the general term “value documents”. without being understood in a limiting sense.
  • Classification methods are used in particular in the recognition and subsequent sorting of banknotes in banknote processing devices.
  • physical variables of the banknote to be classified are first measured and from this a large number of properties (also called properties) of the banknote are derived.
  • properties also called properties
  • a class is then determined with the aid of classification or adaptation parameters, ie selected from several possible classes, and the banknote is assigned to this class.
  • the banknote can then be issued in an output compartment provided for the corresponding class.
  • a digital image of a banknote or a region thereof is taken by means of a suitable imaging sensor unit, for example a CCD or CMOS sensor.
  • Such a digital banknote image consists of individual pixels ("pixels") with associated pixel or intensity values, wherein the pixels of colored images are generally assigned three pixel values.
  • This banknote image is fed in electronic form to a control and evaluation device of the banknote processing apparatus and can be used by it in addition to other measured properties of the banknote for the classification of the banknote.
  • an optical or physical property of the banknote is determined quantitatively on the basis of the digital image of the banknote or a part thereof by means of the control and evaluation device of the banknote processing device, for example an averaged intensity value in a specific area of the banknote image, and with an associated parameter, eg a Threshold, compared to a given set of classification parameters.
  • digital banknote images are well-suited for determining a variety of banknote properties, such as determining the denomination of a banknote, certain properties can be determined only to a very limited extent by means of a digital image of a banknote. Therefore, for example, a thickness sensor in the form of an ultrasonic sensor is usually used to detect adhesive strips on a banknote. It is desirable to detect and, if necessary, sort out taped banknotes, since banknotes provided with adhesive strips can easily lead to congestion in cash dispensers.
  • a banknote processing apparatus can be used to process banknotes, ie in particular to classify, count and sort banknotes
  • a set of classification parameters must be created for the banknotes to be processed and stored, for example, in the control and evaluation apparatus of the banknote processing apparatus.
  • This process is also known to the person skilled in the art as an adaptation of a banknote processing device.
  • the art in adaptation is to select the classification or adaptation parameters such that, for as many banknotes as possible, the class determined by the control and evaluation unit is equal to the "actual" class of a banknote.
  • the classification or adaptation parameters determine the distribution of the banknotes over the classes defined by the classification parameters.
  • the object of the present invention is to provide an improved method and a corresponding apparatus for determining classification parameters for the classification of bank accounts. in particular in a banknote processing device with a sensor unit for the detection of banknotes with adhesive strips.
  • the inventive method for determining a set of classification parameters or adaptation parameters for the classification of banknotes into different classes by means of a banknote processing device comprises the following steps.
  • Determining a set of classification parameters Determining the distribution of the plurality of reference banknotes on the different classes based on the measurement data of the reference banknotes and the set of classification parameters.
  • a distance measure used which must be minimized.
  • the measurement data recorded by the sensor device of the banknote processing device for a plurality of reference banknotes preferably contains optical measurement data, in particular image data, of the reference banknotes recorded by means of an optical sensor unit of the sensor device, as well as measurement data recorded by means of an ultrasound sensor unit of the sensor device.
  • the reference banknotes provided with an adhesive strip are configured such that these reference banknotes contain additional information for determining a classification parameter relating to the measurement data of the ultrasound sensor unit, which can be determined by means of the optical sensor unit and for determining the classification parameter relating to the measurement data of the ultrasound sensor unit can be used.
  • the adhesive strips are colored in the reference banknotes with an adhesive strip, preferably with a color stands out from the colors that the background of the reference bank note has in the vicinity of the colored adhesive strip, so that, for example, a respective adhesive strip surface can easily be determined by means of the measurement data acquired by the optical sensor unit.
  • the adhesive strips on the reference banknotes can be colored, the adhesive strips occupying different areas on the reference banknotes and having different colors, so that there is a clear association between the area and the color of an adhesive strip which is used for this purpose to derive its surface due to the color of an adhesive tape.
  • the reference banknotes with an adhesive strip have the additional information for the determination of one of the measurement data of the ultrasound sensor unit
  • Classification parameters which can be determined by means of the optical sensor unit and used to determine the classification parameter relating to the measurement data of the ultrasonic sensor unit, in the form of a numerical sequence, a nominal value, a graphic motif, a bar code or the like.
  • the additional information for determining a classification parameter relating to the measurement data of the ultrasonic sensor unit which can be determined by the optical sensor unit and used to determine the classification parameter relating to the measurement data of the ultrasonic sensor unit, instead of the area information or in addition to this more information about one Adhesive strips, such as the position, thickness, extent and / or shape of an adhesive strip on a reference banknote.
  • the classification parameters determined according to the method described above can be used advantageously in a method for classifying banknotes, comprising the following further steps: determining at least one quantitative property of a banknote to be classified; and classifying the banknote to be classified on the basis of the quantitative property of the banknote to be classified and the classification parameters.
  • the possible classes from which one is to be selected are, for example, the denominations of the different banknotes. Possible classes can then be provided for example for 5, 10, 20, 50, 00, 200 and 500 euro bills.
  • the determination of a class may also be additional in terms of authenticity and / or fitness, i. H. the suitability of the banknote for reuse, this classification also being able to depend on whether a banknote has an adhesive strip or not.
  • the individual possible classes then additionally reflect, for example, different authenticity or fitness levels of the value documents to be classified, such as "genuine”, “marketable”, “to be destroyed” and the like.
  • a control and evaluation device can in principle ell as any analog, mixed analog-digital or purely digital circuit designed. It is also possible that this alone comprises a so-called "field programmable gate array" (FPG A), which has the advantage that corresponding components can be adapted solely by pre-programming for the method to be carried out, but during implementation how to work a digital circuit. In this way, the production costs can be kept low for small batches.
  • FPG A field programmable gate array
  • the control and evaluation device preferably has at least one processor and a memory in which a computer program executable with the processor according to the invention for carrying out the method according to the invention is stored.
  • processor in the context of the invention, any processor, such as a microcontroller or a general purpose processor or a digital signal processor, or a combination with a general purpose processor and / or a signal processor and / or a microcontroller and / or a FPGA understood.
  • a computer program for carrying out the method according to the invention can be stored in particular in the memory of the control and evaluation device.
  • the data medium carriers are, in particular, optical data carriers such as, for example, CD or DVD, magneto-optical data carriers, magnetic data carriers, such as For example, hard disks and semiconductor memory, such as EEPROMs or flash memory into consideration, the content of which can be accessed by a corresponding device of a computer.
  • the control and evaluation device is connected to an external computer with a display unit according to a preferred embodiment.
  • the external computer implements a graphical user interface that is known to interact with the user.
  • the external computer may also be connected to an external database for storing data, in particular measurement data. In other embodiments, the external computer and / or the external database may be integrated into the control and evaluation device.
  • FIG. 1 is a schematic illustration of a bank note processing apparatus, a flowchart illustrating the steps of a method for adapting and classifying bank notes according to a preferred embodiment of the invention
  • 3 shows a schematic illustration of an exemplary reference banknote of a plurality of reference banknotes for carrying out an adaptation with the banknote processing device of FIG. 1
  • FIG. 4 shows the signal value measured by means of an ultrasound sensor unit for determining the thickness of the reference banknote of FIG. 3 as a function of the position along the reference banknote ,
  • FIG. 1 shows a device 10 for determining a set of classification or adaptation parameters and for classifying and correspondingly processing banknotes, in short, a banknote processing device 10.
  • the device 10 has an input pocket 14 for the input of banknotes 12 to be classified a stack and a separating device 16 known to the person skilled in the art, which can access the banknotes 12 in the input compartment 14 and supply them to a transport system 18 with a diverter 20. Downstream of the switching device 20 along a first branch of the transport system 18 there are a plurality of output compartments 22a-c, which in turn in each case a switch device (not shown) is connected upstream to direct a banknote 12 in one of the output compartments 22a-c.
  • the apparatus 10 has a reject bin 24 along a second branch of the rejected bank transport system 18.
  • a banknote processing apparatus may also have more or fewer output compartments, for example one output compartment each for the denominations occurring in a currency.
  • a banknote 12 to be classified passes through the separation input. direction 16 and in front of the switch device 20, the field of view of a sensor device 26, which serves to detect physical characteristics isolated banknotes supplied 12 and to form corresponding sensor signals or measurement data.
  • a control and evaluation device 30 is in particular connected to the sensor device 26, the switch device 20 and the switch devices, which are connected upstream of the output compartments 22a-c via data and / or signal connections, as indicated in Figure 1 by double arrows, and is used for evaluating the sensor signals or measurement data of the sensor device 26 and for controlling, for example, the switch device 20 and the switch devices upstream of the output sections as a function of the results of the evaluation of the sensor signals.
  • the sensor device 26 preferably comprises an optical sensor unit 26a for detecting optical properties and a sensor unit 26b for determining the local thickness of a banknote, preferably an ultrasonic sensor unit 26b, which is particularly suitable for banknote defects such as adhesive strips, cracks, dog-ears and the like detect.
  • the optical sensor unit 26a comprises at least one imaging optical sensor which, in combination with an optical device 28a known to the person skilled in the art, for example a lens arrangement, serves for detecting optical properties of isolated banknotes 12 and for forming corresponding sensor signals or measurement data.
  • the optical sensor unit 26a is configured to produce a digital image of at least a portion of a banknote 12, preferably the entire banknote 12, by means of optical radiation remitted from and / or passing through the banknote 12 (Transmission).
  • the device 10 further comprises at least one suitably designed and relative to the banknote 12 and the optical sensor unit 26a suitably arranged light source (not shown).
  • the imaging optical sensor is preferably a CCD or CMOS sensor, which preferably produces a digital image of the entire banknote 12, which consists of individual pixels or pixels with associated pixel or intensity values.
  • each pixel typically has more than one pixel or color coordinate value.
  • the optical sensor unit 26a can be designed so that an image is acquired simultaneously for the entire banknote 12.
  • one sensor line of the optical sensor unit 26a to capture line by line image data of a banknote 12 moved past the sensor line and to combine the image data thus acquired into a digital image of the banknote 12.
  • the image data for a pixel comprise the pixel value or, in the case of colored images, the pixel or color coordinate values (for example in the CIE-XYZ color space) and the location or the position of the pixel on the banknote.
  • a suitable color detection device which can be used as the optical sensor unit 26a in the bank note processing device 10 according to the invention is described, for example, in the international patent application WO 2006/018283.
  • pixel or color coordinate values can be generated in any manner.
  • the color coordinate values can be obtained either directly or after transformation of other acquired image data by using suitable sensor or detection units.
  • any color spaces can be used.
  • color spaces with three dimensions are used, but it is also possible to use even higher-dimensional color spaces.
  • a color space specific to the optical sensor device 26a used for imaging may also be used.
  • the color space used can be, for example, the RGB or the HSI color space.
  • a device-independently defined color space is used as the color space.
  • the sensor device 26 comprises, in addition to the optical sensor unit 26a, a sensor unit 26b for determining the local thickness of a banknote as a function of the position along the banknote, which is preferably configured as an ultrasound sensor unit 26b and is particularly suitable for detecting banknotes with adhesive strips ,
  • the ultrasonic sensor unit 26b preferably comprises a device 28b for generating an ultrasonic pulse, by means of which the local thickness of a banknote as a function of the position along the banknote can be determined.
  • the ultrasonic sensor unit 26b further comprises a corresponding unit, which detects the ultrasonic pulse transmitted and / or reflected by the banknote and generates a corresponding signal.
  • a corresponding unit which detects the ultrasonic pulse transmitted and / or reflected by the banknote and generates a corresponding signal.
  • the device 10 may also have further sensor units, such as optical sensors operating in other wavelength ranges (eg infrared), sensors for determining magnetic and / or other physical properties, and the like, the part of the sensor device 26 or each may be formed as a separate component.
  • optical sensors operating in other wavelength ranges (eg infrared)
  • sensors for determining magnetic and / or other physical properties e.g infrared
  • the part of the sensor device 26 or each may be formed as a separate component.
  • At least one quantitative banknote characteristic is determined by the control and evaluation device 30.
  • a plurality of these properties or properties are determined and, if appropriate, suitably linked to one another, for example by means of linear combinations of properties.
  • the authenticity of the banknotes is checked by means of the signals or measured data of the optical sensor unit 26a and the ultrasonic sensor unit 26b of the sensor device 26 and possibly further sensor units of the sensor device 26.
  • control and evaluation device 30 has, in addition to corresponding interfaces for the sensor device 26, a processor 32 and a memory 34 connected to the processor 32 in which at least one computer program 36 is stored with program code, in the execution of which the processor 32 sensor signals or measurement data, in particular for determining a class of a banknote to be classified, evaluates and controls the device 10 and its components accordingly.
  • the control and evaluation device 30, more precisely the processor 32 therein is designed, after the quantitative determination of at least one property of a banknote 12 to be classified, to check into which class of a plurality of different classes the banknote 12 to be classified falls for example, by checking whether the quantified property falls within the tolerance range of a classification parameter of a class that is part of a set of classification parameters. If, in this case, a quantitatively determined property of a banknote to be classified falls within the tolerance range of a classification parameter, then the control and evaluation device 30 assigns the banknote to the class which is defined by this classification parameter.
  • the control and evaluation device 30 controls the control and evaluation device 30, in particular the processor 32 therein the transport system 18, the switch device 20 and the output compartments 22a-c upstream switching devices so that the checked banknote according to their determined class for storage in a the output trays 22a-c or for re-manual check or for sorting in the reject tray 24 is transported.
  • control and evaluation unit 30 of the banknote processing device 10 is configured to perform the method described below in FIG. 2 with reference to a flowchart for the determination of classification parameters or adaptation parameters and for the classification of banknotes.
  • This method or parts thereof consisting of an adaptation and a classification are preferably carried out by means of the computer program 36, which is stored in the memory 34 of the control and evaluation unit 30 and accesses its processor 32.
  • the method shown in FIG. 2 or parts thereof may be performed on an external computer 38 connected to the control and evaluation unit 30, which in turn may be connected to a database 40 for storing large amounts of data.
  • a multiplicity of reference banknotes are processed by means of the banknote processing device 10 and measurement data is acquired by the sensor device 26 and sent to the control and evaluation unit 30 by means of corresponding sensor signals transfer.
  • a digital optical image of a banknote is detected by the optical sensor unit 26a of the sensor device 26, and the progression of the local thickness of the banknote as a function of the position on the banknote in the form of an "ultrasound image" is detected by the ultrasound sensor unit 26b.
  • the reference banknotes are preferably provided with an adhesive strip.
  • step S2 of FIG. 2 which may be, for example, a first approximation of an optimum set of classification parameters determined in a previous adaptation of the device 10
  • step S3 of FIG. 2 determines how the reference banknotes are distributed over the classes defined by the first set of classification parameters on the basis of their measurement data determined in step S1. In this case, the determination of the distribution, for example, by the tax and evaluation device 30 or the external computer 38 are made.
  • the reference banknotes are selected so that their properties are known, it is also known to which class a respective reference banknote belongs or should belong. This known affiliation of the reference banknotes to the different classes defines the optimal distribution of the reference banknotes across the different classes.
  • the distribution of the reference banknotes determined by the measurement data in step S3 of FIG. 2 over the classes defined by the first set of classification parameters, which is also referred to below as simulated distribution of the reference banknotes is determined by the optimal distribution of the reference banknotes over the differ in different classes. Whether this is the case is checked in step S4 of FIG.
  • the simulated distribution is compared with the optimal distribution of the reference banknotes over the different classes in step S4 of Figure 2 by defining a distance measure between the simulated distribution and the optimal distribution of the reference banknotes across the different classes.
  • a simple distance measure may be defined by considering a particular property that enters the distribution of reference banknotes (e.g.
  • the bill handling apparatus 10 includes an ultrasonic sensor unit 26b adjacent to the optical sensor unit 26a, the following pitch measures may be used, for example: - F measured ⁇
  • D stands for the "distance”
  • Fabsohu for the actual area of an adhesive strip
  • FMSessen for the measured area of the adhesive strip on a reference banknote and the sum is formed over all reference banknotes.
  • a multiplicity of further distance dimensions are conceivable, into which further measured and actual properties of the reference banknotes can flow.
  • a distance measure has been calculated, it can be determined in step S5 of FIG. 2 whether the distance calculated for a given distance measure Distance is less than a defined threshold.
  • step S6 of FIG. 2 the set of classification parameters is adjusted so that this discrepancy is reduced.
  • the distance defined by a suitable distance measure, between the simulated and the actual distribution of the reference banknotes over the different classes as a function of the classification parameters must be optimized, ie minimized.
  • an optimization method for nonlinear optimization is used, such as a downhill simplex method with or without step size control, a simulated annealing method, or the like.
  • an evolutionary optimization algorithm is also possible.
  • the "genetic material” of the individuals consists of the classification parameters, whereby the individuals are subject to recombination (exchange of parts of the "genetic material"), mutation (minor changes) and selection (evaluation of the quality, distance measure).
  • the above-described optimization problem for acceleration can be divided into subproblems.
  • the classification parameters for the detection of cracks and / or holes are largely independent of the classification parameters for the detection of adhesive strips.
  • the respective groups of classification parameters can therefore preferably be optimized separately from each other.
  • the optimization or minimization of the distance, defined by a suitable distance measure, between the simulated and actual distribution of the reference banknotes over the different classes as a function of the classification parameters incorporates the expert knowledge gained in earlier adaptations.
  • This expert knowledge is preferably stored and maintained as a knowledge database in the form of decision rules, for example in the control and evaluation device 30 or the external computer 38 or the associated database 40.
  • This knowledge database makes it possible, in step S6 of FIG. 2, to pre-select from the various conceivable changes in the classification parameters even before the simulated distribution of the reference database is recreated. 2 to meet about the different classes in step S3 of Figure 2 and thus to speed up the optimization process.
  • step S5 of Figure 2 In the event that no or only an acceptable discrepancy between the simulated and the actual distribution of the reference banknotes on the different classes is determined in step S5 of Figure 2, for example, as described above, by means of a suitable distance measure, that is for the preparation of simulated distribution of the reference banknotes over the different classes used in step S3 of Figure 2 and possibly adjusted before in step S6 of Figure 2 appropriate set to be used for the classification of banknotes to be processed with the banknote processing apparatus 10, in the steps S7 and S8 of Figure 2 is done.
  • the measurement data of a plurality of banknotes to be classified are recorded with the optical sensor unit 26a and the ultrasonic sensor unit 26b in step S7 of FIG. On the basis of these respective measurement data, in step S8 of FIG.
  • a respective banknote to be classified is assigned to a class defined by the optimized set of classification parameters and fed to one of the output bins 22a-c or the reject bin 24 of the banknote processing device 10 according to this allocation.
  • this allocation is preferably made by the control and evaluation device 30 of the banknote processing apparatus 10.
  • the steps S 1 to S 6 illustrated in FIG. 2 form a method for determining an optimized set of classification or adaptation parameters (identified as part "A" in FIG. 2) as part of a separate adaptation process and shown in FIG 2, steps S7 and S8 show a method of classifying, in the "actual" operation of the banknote processing apparatus 10 Banknotes by means of this optimized set of classification or adaptation parameters (marked as part "B" in FIG. 2).
  • FIG. 3 shows a schematic representation of an exemplary reference banknote 100 of a set of reference banknotes that can be used to carry out the method described above in connection with FIG. 2 for determining an optimized set of classification parameters.
  • Exemplary reference banknote 100 includes, by way of example, a motif 102, a serial number 104 and the nominal value 106 of reference banknote 100, which can be recorded well with optical sensor unit 26. Also located on the reference banknote 100 is a first adhesive strip 110 and a second adhesive strip 112.
  • the measurement spot defined by an element of the sensor line of the ultrasound sensor unit 26b moves parallel to the direction of movement of the reference banknote 100 along the reference banknote 100 and thereby defines an exemplary measurement lane 108.
  • the measurement lane 108 along this exemplary measurement lane 108 an element of the sensor line of the ultrasonic sensor unit 26b measured signal value or intensity profile is shown schematically in Figure 4.
  • the entire sensor line of the ultrasonic sensor unit 26b provides a plurality of such intensity traces that can be combined to form an "ultrasound image" of the bill 100 that provides information about the local thickness of the bill 100 as a function of position on the bill 100 ,
  • the exemplary measuring track 108 in the exemplary reference banknote 100 particularly detects the motif 102, the first adhesive strip 110 and the second adhesive strip 112.
  • the features are reflected in corresponding features in the intensity curve shown in FIG. 4, namely in intensity peaks of different intensity at the positions x1, x2 and x3.
  • FIG. 4 also shows three different intensity threshold values y1, y2 and y3. It is conceivable that these three different intensity threshold values y1, y2 and y3 are used as classification parameters in the method for determining a set of classification parameters described above in connection with FIG. 2 or at least incorporated into such a classification parameter. For example, the three different intensity thresholds y1, y2, and y3 could be used to determine whether a banknote has or does not have an adhesive strip and / or to determine the size of an adhesive strip on a banknote. The person skilled in the art will recognize that in the exemplary intensity profile illustrated in FIG.
  • the control and evaluation device 30 would arrive at the result that the reference banknote 100 has three, two or only has an adhesive strip. Likewise, depending on the choice of the intensity threshold or classification parameter (y1, y2 or y3), the control and evaluation device 30 would have different results regarding the size or area of the adhesive strips present on the reference banknote 100.
  • a preferred embodiment of the present invention is based on the further consideration of configuring the reference banknotes used in the method for determining classification parameters in such a way that they contain additional information for determining a classification parameter relating to the measurement data of the ultrasound sensor unit 26b, which by means of the optical sensor unit 26a can be determined and used to determine a classification parameter relating to the measurement data of the ultrasonic sensor unit 26b.
  • this additional information for determining a classification parameter relating to the measurement data of the ultrasound sensor unit 26b can be contained in the reference banknotes in that the usually transparent adhesive strips are colored, preferably with a color which stands out from the color (s) has the background of the reference banknote in the vicinity of the colored adhesive strip.
  • the area occupied by a respective adhesive strip on a reference banknote can be determined by the control and evaluation device 30 without difficulty on the basis of the measurement data acquired by means of the optical sensor unit 26a.
  • a corresponding classification parameter is then selected so that the areas of the adhesive strips determined by means of the measurement data of the optical sensor unit 26a fit as well as possible to the surfaces of the adhesive strips determined by the measurement data of the ultrasonic sensor unit 26b.
  • the areas of the adhesive strips determined by means of the measurement data of the optical sensor unit 26a could be used to select the intensity threshold value in such a way that based on the measurement data of the ultrasound sensors. Sorica 26b corresponding areas for the adhesive strip at the position x2 and the adhesive strip are determined at the position x3.
  • the reference banknotes are configured in such a way that the additional information for determining a classification parameter relating to the measurement data of the ultrasound sensor unit 26b is contained in the reference banknotes in a different manner so that it determines by means of the optical sensor unit 26a and can be used to determine a classification parameter relating to the measurement data of the ultrasonic sensor unit 26b.
  • the adhesive strips on the reference banknotes may in turn be colored, the adhesive strips occupying different areas on the reference banknotes and having different colors, as indicated in FIG. 3 by the different patterns of the adhesive strips 110 and 112, so that between the surface and the color of an adhesive strip is a unique assignment.
  • information can be stored, for example, in the control and evaluation device 30, which color corresponds to which surface of an adhesive strip.
  • a blue adhesive strip covers an area of 10% of the area of the reference banknote, a red adhesive strip an area of 5% of the area of the reference banknote and a green adhesive strip an area of 2% of the area of the reference banknote having.
  • control and evaluation device 30 having determined the color of an adhesive strip, knows its area and, on the basis of this information, as described above, can select a corresponding classification parameter such that the areas of the adhesive strips determined by the measurement data of the optical sensor unit 26a are fit as well as possible to the surfaces of the adhesive strips determined by the measurement data of the ultrasonic sensor unit 26b.
  • this information in the form of a number sequence (eg, the serial number 104 shown in Figure 3), a nominal value (eg, the nominal value 106 shown in Figure 3), a graphic motif (eg, the in FIG 3 illustrated motif 102), a barcode or the like and can be extracted from the measured data of the optical sensor unit 26a.
  • a number sequence eg, the serial number 104 shown in Figure 3
  • a nominal value eg, the nominal value 106 shown in Figure 3
  • a graphic motif eg, the in FIG 3 illustrated motif 102
  • the additional information for determining a classification parameter relating to the measurement data of the ultrasonic sensor unit 26b which are deposited on the reference banknotes such that they can be determined by the optical sensor unit 26a and used to determine a classification parameter relating to the measurement data of the ultrasonic sensor unit 26b instead of the area information or in addition to this information about an adhesive strip, such as the position, thickness, extent and / or shape of an adhesive strip on a Referenzbankno- te.
  • control and evaluation unit 30 of the banknote processing device 10 is preferably connected to an external computer 38 connected to a display unit in the form of a screen.
  • a graphical user interface is preferably implemented, by means of which a user can perform, for example, the method described above for determining a set of classification parameters and, if necessary, intervene. It is conceivable, for example, for the graphical user interface to be configured such that a user can readjust classification parameters by means of the graphical user interface.
  • the external computer 38 may also be connected to an external database 40 for storing large amounts of data, in particular image data. In other embodiments, it is also conceivable that the external computer 38 and / or the external database 40 are part of the control and evaluation device 30.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Toxicology (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

La présente invention concerne un procédé pour déterminer un ensemble de paramètres de classement ou de paramètres d'adaptation pour le classement de billets de banque en différentes classes au moyen d'un dispositif de traitement de billets de banque. Le procédé comprend les étapes suivantes : enregistrement de données de mesure pour une pluralité de billets de banque de référence avec des caractéristiques connues au moyen d'un dispositif de captage du dispositif de traitement de billets de banque, au moins quelques-uns des billets de banque de référence étant pourvus d'une bande collante ; détermination d'un ensemble de paramètres de classement ; détermination de la répartition de la pluralité de billets de banque de référence selon les différentes classes à l'aide des données de mesure des billets de banque de référence et de l'ensemble de paramètres de classement ; comparaison de la répartition selon les différentes classes, déterminée pour la pluralité de billets de banque de référence, avec la répartition optimale des billets de banque de référence selon les différentes classes, déterminée à partir des caractéristiques connues de la pluralité de billets de banque de référence ; adaptation, si les deux répartitions diffèrent l'une de l'autre, de l'ensemble de paramètres de classement jusqu'à ce que la répartition de la pluralité de billets de banque de référence sur les différentes classes, déterminée à l'aide des données de mesure des billets de banque de référence et de l'ensemble modifié de paramètres de classement, et la répartition optimale des billets de banque de référence selon les différentes classes, déterminée à partir des caractéristiques connues de la pluralité de billets de banque de référence, ne diffèrent plus l'une de l'autre ou jusqu'à ce que la différence entre ces répartitions soit acceptable.
EP12813766.8A 2011-12-21 2012-12-18 Procédé et dispositif pour déterminer des paramètres de classement pour le classement de billets de banque Withdrawn EP2795592A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102011121877A DE102011121877A1 (de) 2011-12-21 2011-12-21 Verfahren und Vorrichtung zur Bestimmung von Klassifizierungsparametern für die Klassifizierung von Banknoten
PCT/EP2012/005239 WO2013091841A1 (fr) 2011-12-21 2012-12-18 Procédé et dispositif pour déterminer des paramètres de classement pour le classement de billets de banque

Publications (1)

Publication Number Publication Date
EP2795592A1 true EP2795592A1 (fr) 2014-10-29

Family

ID=47557013

Family Applications (1)

Application Number Title Priority Date Filing Date
EP12813766.8A Withdrawn EP2795592A1 (fr) 2011-12-21 2012-12-18 Procédé et dispositif pour déterminer des paramètres de classement pour le classement de billets de banque

Country Status (4)

Country Link
US (1) US9449255B2 (fr)
EP (1) EP2795592A1 (fr)
DE (1) DE102011121877A1 (fr)
WO (1) WO2013091841A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102013010741A1 (de) 2013-06-27 2014-12-31 Giesecke & Devrient Gmbh Verfahren zur Bereitstellung von Messdaten einer Vorrichtung zur Bearbeitung von Wertdokumenten und Wertdokumentbearbeitungsvorrichtung
DE102013021655A1 (de) 2013-12-18 2015-06-18 Giesecke & Devrient Gmbh Verfahren und Vorrichtung zur Bearbeitung von Wertdokumenten
EP3007133B1 (fr) * 2014-10-08 2018-06-20 OCE-Technologies B.V. Appareil et procédé de détection de défaut dans un système d'impression
CN106934921B (zh) * 2017-02-22 2019-12-31 广州广电运通金融电子股份有限公司 纸张类异物粘贴检测方法及装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05262312A (ja) * 1991-06-04 1993-10-12 Ncr Corp 用紙取り扱い装置
GB2284293B (en) * 1993-11-30 1998-06-03 Mars Inc Article classifying method and apparatus
US5636565A (en) * 1995-12-14 1997-06-10 Lawrance; Michael Embossing method and device for braille currency encoding
GB2341263B (en) * 1998-08-14 2002-12-18 Mars Inc Method and apparatus for validating currency
DE10151854A1 (de) * 2001-10-24 2003-05-08 Giesecke & Devrient Gmbh Wertdokumentbearbeitungsvorrichtung, Verfahren zur Funktionsprüfung, Justierung und/oder Kalibrierung der Wertdokumentbearbeitungsvorrichtung und Testmedien zur Durchführung des Verfahrens
US7028888B2 (en) * 2001-11-05 2006-04-18 Diebold Incorporated Automated banking machine currency tracking system
US7433844B2 (en) * 2001-11-05 2008-10-07 Diebold, Incorporated Automated banking machine currency tracking method
DE10231409A1 (de) * 2002-07-11 2004-01-22 Giesecke & Devrient Gmbh Verfahren für die Einstellung einer Banknotenbearbeitungsmaschine
DE10314071B3 (de) 2003-03-28 2004-09-30 Koenig & Bauer Ag Verfahren zur qualitativen Beurteilung eines Materials mit mindestens einem Erkennungsmerkmal
DE102004024620A1 (de) 2004-05-18 2005-12-08 Giesecke & Devrient Gmbh Vorrichtung und Verfahren zur Prüfung von Banknoten
DE102004059951A1 (de) 2004-08-17 2006-02-23 Giesecke & Devrient Gmbh Vorrichtung zur Untersuchung von Dokumenten
DE102006033001A1 (de) * 2006-07-17 2008-01-24 Giesecke & Devrient Gmbh Verfahren zur Beurteilung eines Zustands eines Wertdokuments im Hinblick auf Lappigkeit und Mittel zur Durchführung des Verfahrens
DE102006053788A1 (de) 2006-11-15 2008-05-21 Giesecke & Devrient Gmbh Verfahren zur Erkennung von Verschmutzungen im Bereich von Farbübergängen auf Wertdokumenten und Mittel zur Durchführung des Verfahrens
DE102007019107A1 (de) 2007-04-23 2008-10-30 Giesecke & Devrient Gmbh Verfahren und Vorrichtung zur Prüfung von Wertdokumenten
DE102008041944A1 (de) * 2008-09-10 2010-03-11 Bundesdruckerei Gmbh Datenverarbeitungsverfahren zur Generierung eines Klassifikators und zur Überprüfung der Echtheit eines Dokuments, Vorrichtung zur Überprüfung der Echtheit eines Dokuments und Computerprogrammprodukt
JP2010257338A (ja) * 2009-04-27 2010-11-11 Toshiba Corp 紙葉類処理システム

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
None *
See also references of WO2013091841A1 *

Also Published As

Publication number Publication date
WO2013091841A1 (fr) 2013-06-27
US9449255B2 (en) 2016-09-20
US20140348413A1 (en) 2014-11-27
DE102011121877A1 (de) 2013-06-27

Similar Documents

Publication Publication Date Title
EP2095341B1 (fr) Procédé de détection des encrassements et/ou l'usure de l'encre dans la zone des transitions de couleur sur des documents de valeur et moyens en vue de mettre en oeuvre le procédé
DE2824849C2 (de) Verfahren und Vorrichtung zur Feststellung des Zustandes und/oder der Echtheit von Blattgut
WO2012084145A1 (fr) Procédé et dispositif de détermination d'un ensemble de données de référence de classe, pour la classification de documents de valeur
DE4437067A1 (de) Neutrales, Zufallsmasken benutzendes Banknotenerkennungssystem, und Verfahren zur Maskenoptimierung für Muster-Erkennung nach Vererbungsalgorithmus
EP1652153B1 (fr) Dispositif de determination de l'etat de billets de banque
EP2143081B1 (fr) Procédé et dispositif pour vérifier des documents-valeurs
EP1610270A2 (fr) Procédé d'évaluation d'un materiel avec au moins une caractéristique d'identification
WO2013091841A1 (fr) Procédé et dispositif pour déterminer des paramètres de classement pour le classement de billets de banque
EP3111426B1 (fr) Procédé de détermination d'un résultat de tri pour un document de valeur et moyen de mise en oeuvre du procédé
EP2761604A1 (fr) Procédé de contrôle de la qualité de fabrication d'une caractéristique de sécurité d'un document de valeur
DE102009058438A1 (de) Verfahren zur Prüfung von Wertdokumenten
EP3084732A1 (fr) Procédé et dispositif pour le traitement de documents de valeur
EP2656327B1 (fr) Procédé et dispositif pour l'examen de l'état optique de documents de valeur
EP2920769B1 (fr) L'appareil et methode pour evaluer les documents de valeur
EP3014589B1 (fr) Methode pour mettre a disposition des donnees de mesure d'un dispositif de traitement de documents de valeur et dispositif de traitement de documents de valeur
DE102009058439A1 (de) Verfahren zur Prüfung von Wertdokumenten
EP3134878B1 (fr) Procede de verification d'un document de valeur
EP3170154B1 (fr) Procédé et dispositif de vérification de conformité de documents de valeur
EP3563357A1 (fr) Procédé et dispositif permettant de détecter un fil de sécurité dans un document de valeur
EP3563356A1 (fr) Procédé et dispositif permettant de détecter un fil de sécurité dans un document de valeur
EP2676248B1 (fr) Dispositif de manipulation de billets et de chèques
DE102012025417A1 (de) Verfahren zur Erkennung von Individualkennungen, insbesondere Seriennummern, auf Wertdokumenten und Mittel zur Durchführung des Verfahrens
DE102020004284A1 (de) Verfahren und Vorrichtung zum Prüfen von Wertdokumenten und Verfahren und Vorrichtung zum Erzeugen von Prüfparametern zur Verwendung bei einem Verfahren zum Prüfen von Wertdokumenten
WO2014029476A1 (fr) Procédé et dispositif de contrôle de documents fiduciaires
EP2786356B1 (fr) Pocede et systeme de traitement de billets de banque

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20140721

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAX Request for extension of the european patent (deleted)
17Q First examination report despatched

Effective date: 20161130

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

RIC1 Information provided on ipc code assigned before grant

Ipc: G07D 11/00 20060101ALI20170201BHEP

Ipc: G06K 9/62 20060101ALI20170201BHEP

Ipc: G07D 7/08 20060101ALI20170201BHEP

Ipc: G07D 7/12 20160101ALI20170201BHEP

Ipc: G07D 7/00 20160101AFI20170201BHEP

INTG Intention to grant announced

Effective date: 20170301

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: GIESECKE+DEVRIENT CURRENCY TECHNOLOGY GMBH

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20170712