EP3539091B1 - Device and method for classifying value documents, in particular bank notes, and value document processing system - Google Patents

Description

The invention relates to a device and a method for classifying documents of value and a document processing system of value with such a device.

In the machine processing of documents of value, for example banknotes, checks, coupons or vouchers, these are often classified, for example with regard to denomination, authenticity and / or condition, and further processed depending on the result of the classification, for example sorted. For this purpose, properties of the value documents are recorded by means of sensors. A processor unit is assigned to each of the sensors, in which the raw data generated by the respective sensor are subjected to a preliminary evaluation. On the basis of the results of the preliminary evaluations in the different processor units, a classification of the respective value document is then carried out in a central instance and this is sorted accordingly.

The JP 2004 355261 A shows an image detector for paper currency.

The WO 98/40839 A2 shows an automatic document processing system that utilizes full screen scanning.

The DE 10 2009 057 348 A1 discloses a method and apparatus for validating bank notes.

It is the object of the present invention to make the classification of documents of value more reliable and efficient.

This object is achieved by the device and the method for classifying documents of value according to the independent claims and the document processing system with such a device.

A device is described for classifying documents of value, in particular banknotes, which has at least two sensor devices which are set up to generate waves, in particular electromagnetic waves, which are reflected on a front side and on a rear side of a document of value Waves, to detect and to generate corresponding sensor data or to detect properties of the value document in at least two different regions of the value document by means of different measurement principles and to generate corresponding sensor data. At least one evaluation device is set up to use the sensor data generated by the at least two sensor devices that relate to the waves reflected on the front and back of the document of value or to the properties of the document of value recorded in the at least two different regions of the document of value by means of different measurement principles. to classify.

The value document processing system according to the invention has: a device according to the invention for classifying documents of value and a sorting device which has different sorting compartments and is set up to output the value documents into the different sorting compartments as a function of the classification made using the sensor data.

The inventive method for classifying documents of value has the following steps: detecting waves, in particular electromagnetic waves, reflected on a front and back of a document of value, and generating corresponding sensor data or detecting properties of the document of value in at least two different regions of the document of value by means of different measurement principles and generating corresponding sensor data; Classifying the value document on the basis of the generated sensor data, which the waves reflected on the front and back of the value document or those in the at least two different regions of the value document by means of different measurement principles affect properties of the document of value.

One aspect of the invention is based on the approach of combining sensor data from several sensor devices in an evaluation device, evaluating the merged sensor data in the evaluation device and classifying the value document according to the result of the evaluation of the merged sensor data. The merged sensor data are raw data that are generated by the sensor devices when they detect waves that are reflected, in particular electromagnetic, waves on the front and back of the document of value. Alternatively, the merged sensor data are raw data that are generated by the sensor devices when they detect properties of the value document in at least two different regions of the value document using different measurement principles. As a result of the merging in the evaluation device, the raw data generated by the various sensor devices can be directly linked to one another, for example correlated, when classifying the value document, which allows a particularly reliable classification. In addition, dependencies of the sensor data can be recognized and redundant evaluations, for example in separate processor units, can be avoided. Due to the merging of the sensor data from different sensor devices in one evaluation device, one can also speak of a fusion or amalgamation of the different sensor data or raw data. Since the sensor data of the multiple sensor devices required for a classification of a document of value are present in the respective evaluation device, sensor data can also be copied over or results of a preliminary evaluation of the sensor data can be forwarded to further evaluation devices be waived. This makes the classification particularly efficient.

Overall, the invention thus allows a reliable and efficient classification of documents of value.

Sensor data or raw data in the context of the invention relate to the signals generated by a sensor device, which are generated when a property of a value document is detected. Sensor data thus represent, for example, the reflection and / or transmission behavior of the value document with regard to electromagnetic waves or ultrasonic waves, the electrical conductivity, dielectric or magnetic properties of the value document or at least certain regions of the value document.

The evaluation device has a memory unit for data storage and a control device is provided which is set up to write the sensor data generated by the at least two sensor devices into the memory unit of the at least one evaluation device. As a result, the at least one evaluation device can access the sensor data of all sensor devices at any time and link the sensor data accordingly, so that the classification of the value document based thereon is particularly reliable. In particular, current sensor data from the at least two sensor devices are always present in the memory unit, so that the at least one evaluation device can easily classify the value document using the current sensor data.

The control device is preferably set up to write the sensor data of the at least two sensor devices into the memory unit independently of one another, so that the sensor data can be processed more efficiently. If the sensor devices generate the sensor data, for example, with different clock rates, in particular because the detection of the properties of the document of value is based on different measurement principles and / or the size of different regions in which the properties are detected vary, the sensor data of a sensor device are more often with a higher clock rate , in particular with the higher clock rate, written into the memory device than the sensor data of another sensor device with a lower clock rate.

In a further preferred embodiment, at least two evaluation devices are provided, each of which has a memory unit. In addition, the control device is set up to write the sensor data generated by the at least two sensor devices into each memory unit of the at least two evaluation devices. This ensures that each evaluation device has access to current sensor data from all sensor devices, preferably at any time, and that these sensor data can be linked so that the classification based thereon is particularly precise, i.e. reliable.

In a further preferred embodiment, each of the at least two sensor devices is assigned an evaluation device. This is advantageous, for example, if each of the evaluation devices is set up to carry out a classification with regard to a given class, in particular using a given algorithm, the classification with regard to the given class advantageously being based on sensor data from the sensor device which the respective Evaluation device is assigned. A class within the meaning of the invention relates to a feature of value documents, such as denomination, authenticity or condition. For example, a value document can be classified particularly reliably with respect to its denomination by sensor data of a sensor device that detects optical properties of the value document, while a value document can be classified particularly reliably with respect to its authenticity by sensor data of a sensor device that detects magnetic and / or electrical properties of the value document . Because each sensor device is assigned an evaluation device, the value documents can be classified with respect to different classes at the same time on the basis of the respective advantageous sensor data. However, since the evaluation devices here also have access to other sensor data from other sensor devices, the respectively advantageous sensor data can additionally be linked to other sensor data. This makes the classification even more reliable.

The evaluation devices are preferably set up to classify a document of value with respect to several classes by means of appropriate algorithms. As a result, an evaluation device can, for example, after classifying the document of value with regard to a class, for example on the basis of sensor data from the sensor device assigned to this evaluation device, carry out a further classification with regard to a further class. This is possible since the sensor data of other, in particular all other, sensor devices are available to each evaluation device. This prevents evaluation devices that have carried out a classification particularly quickly from going into an idle state. Classifications of value documents are thus particularly efficient.

In a further preferred embodiment, the sensor devices, which are designed to detect the electromagnetic waves reflected from the front and back of the value document, have a first image sensor and a second image sensor. The first image sensor is preferably set up to capture a remission image of the front side of the document of value and to generate corresponding first image sensor data. The second image sensor is preferably set up to capture a remission image of the back of the document of value and to generate corresponding second image sensor data. The evaluation device is set up to classify the value document on the basis of the first image sensor data and the second image sensor data. This is particularly advantageous if value documents are to be classified with regard to their denominations, since this can be determined particularly reliably using reflectance image data from the front and back, for example by analyzing the captured print image or areas of the print image, such as printed numbers. This design is therefore particularly advantageous in connection with a division into denominations or sorting by denomination. The evaluation device is therefore preferably set up to determine the denomination of the value document on the basis of the first image sensor data and the second image sensor data.

The first image sensor and the second image sensor are preferably designed as a photodiode, CCD or CMOS sensor array.

• einen optischen Sensor, insbesondere einen Bildsensor, welcher dazu eingerichtet ist, optische Eigenschaften des Wertdokuments zu erfassen und entsprechende Sensordaten zu erzeugen,
• einen Ultraschallsensor, welcher dazu eingerichtet ist, Reflexions- und/oder Transmissionseigenschaften des Wertdokuments für Ultraschall zu erfassen und entsprechende Sensordaten zu erzeugen,
• einen kapazitiven Sensor, welcher dazu eingerichtet ist, dielektrische Eigenschaften des Wertdokuments zu erfassen und entsprechende Sensordaten zu erzeugen,
• einen Magnetsensor, welcher dazu eingerichtet ist, magnetische Eigenschaften des Wertdokuments zu erfassen und entsprechende Sensordaten zu erzeugen.

Die Auswertungseinrichtung ist hierbei dazu ausgebildet, das Wertdokument anhand der von den mindestens zwei unterschiedlichen Sensortypen erzeugten Sensordaten zu klassifizieren, welche in den mindestens zwei unterschiedlichen Regionen des Wertdokuments erfasste Eigenschaften des Wertdokuments betreffen. Durch Verknüpfung der für die unterschiedlichen Regionen des Wertdokuments erhaltenen Sensordaten unterschiedlicher Sensortypen kann dieses bezüglich bestimmter Klassen, wie etwa Echtheit, besonders zuverlässig klassifiziert werden.In a further preferred embodiment, the sensor devices, which are designed to detect properties of the document of value in at least two different regions of the document of value by means of different measurement principles, have at least two different sensor types of the following sensor types:

• an optical sensor, in particular an image sensor, which is set up to detect optical properties of the value document and to generate corresponding sensor data,
• an ultrasonic sensor which is set up to detect reflection and / or transmission properties of the document of value for ultrasound and to generate corresponding sensor data,
• a capacitive sensor, which is set up to detect dielectric properties of the value document and to generate corresponding sensor data,
• a magnetic sensor which is set up to detect magnetic properties of the document of value and to generate corresponding sensor data.

The evaluation device is designed to classify the value document on the basis of the sensor data generated by the at least two different sensor types, which relate to properties of the value document recorded in the at least two different regions of the value document. By linking the sensor data of different sensor types obtained for the different regions of the value document, it can be classified particularly reliably with regard to certain classes, such as authenticity.

In a further preferred embodiment, the evaluation device is set up to check the authenticity of the value document on the basis of the sensor data generated by the at least two different sensor types that relate to properties of the value document recorded in the at least two different regions of the value document or to classify the value document accordingly . This is particularly advantageous if different regions of the value document have different security features, which are particularly determined by the respective sensor type can be reliably recorded. In particular, reflected and / or transmitted electromagnetic waves can be detected by an optical sensor, for example an image sensor, in a region of the value document which has an optical security feature, for example a predetermined pattern. In a further region of the value document, which has a security feature to be detected by means of ultrasound, for example a watermark, the thickness of the value document can be detected using a spatially resolving ultrasonic sensor. In another region of the document of value, which has a magnetic security feature, for example lettering printed with magnetic ink, the magnetic field strength can, however, be detected using a magnetic sensor, for example a Hall probe. In a further region of the document of value which has a capacitive or dielectric security feature, for example a metallic security strip, a dielectric constant or a conductivity can be determined using a dielectric sensor, for example a capacitor.

Fig. 1

ein Beispiel einer Vorrichtung zur Klassifizierung von Wertdokumenten in einer schematischen Darstellung;

Fig. 2

ein Beispiel eines Wertdokuments, bei welchem an der Vorderund Rückseite reflektierte Wellen erfasst werden; und

Fig. 3

ein Beispiel eines Wertdokuments, dessen Eigenschaften in unterschiedlichen Regionen erfasst werden.

Further advantages, features and possible applications of the present invention emerge from the following description in conjunction with the figures. Show it:

Fig. 1

an example of a device for classifying documents of value in a schematic representation;

Fig. 2

an example of a value document in which waves reflected on the front and back are detected; and

Fig. 3

an example of a value document whose properties are recorded in different regions.

Figure 1 shows an example of a device 1 for classifying documents of value with a first sensor device 2, a second sensor device 3, a first evaluation device 4, a second evaluation device 5 and a control device 6.

The first sensor device 2 and the second sensor device 3 are set up to detect properties of a value document, for example the transmission and / or reflectivity of the value document with respect to electromagnetic waves or ultrasonic waves, magnetic or dielectric properties of the value document, and in corresponding sensor data 8, so-called raw data to convert. The sensor devices 2, 3 are designed accordingly, for example, as optical sensors, in particular image sensors, piezoelectric ultrasonic sensors, Hall probes or capacitors.

The first and / or second sensor device 2, 3 can preferably detect the properties of the value document in a spatially resolved manner. For this purpose, the sensor devices 2, 3 or at least some of the sensor devices 2, 3 preferably each have a one- or two-dimensional array of sensors, for example semiconductor detectors for detecting electromagnetic waves or piezoelectric elements for detecting ultrasound. Alternatively or additionally, the sensor devices 2, 3 can be set up to scan the value document or at least one region of the value document while the value document and the respective sensor device 2, 3 are moved relative to one another.

The sensor data 8 generated in each case by the sensor devices 2, 3 are stored by the control device 6 in a first memory device 9 of first evaluation device 4 and written into a second memory device 10 of the second evaluation device 5, which is indicated by the arrows. The control device 6 controls the data flow in such a way that the sensor data 8 of both sensor devices 2, 3 are written into each of the memory units 9, 10 of the evaluation devices 4, 5, so that each of the evaluation devices 4, 5 has direct access to the two sensor devices 2, 3 generated sensor data 8 has. As a result, each of the evaluation devices 4, 5 has the option of classifying a value document not only on the basis of the raw data generated by just one sensor device 2 or 3, but also of taking into account the raw data generated by the other sensor device 3 or 2, e.g. by appropriately linking the raw data.

The results 11 of the classification carried out in the evaluation devices 4, 5, which preferably relate to different classes, are transmitted to a central entity 7. For example, the first evaluation device 4 can be set up to classify the value document with regard to its denomination, while the second evaluation device 5 can be set up to classify the value document with regard to its authenticity.

The central instance 7 is preferably set up to control further processing, in particular sorting, of the value document in accordance with the results 11 of the classification. For example, all value documents of a first denomination that have been classified as genuine are output in a first container, while all value documents of a second denomination that have been classified as genuine are output in a second container, etc.

If the central instance 7 only needs one result 11 with regard to a class, for example because documents of value should only be sorted with regard to their denomination regardless of their authenticity or quality, it is also possible to dispense with evaluation devices, for example the second evaluation destruction 5 .

Figure 2 shows an example of a front side 12 and a rear side 13 of a document of value 14 in a schematic representation to illustrate an advantageous application of the in FIG Figure 1 device 1 shown, for example in the separation of denominations.

The first and second sensor devices 2, 3 (see Figure 1 ) detect reflected, in particular remitted, electromagnetic waves on the front side 12 or the rear side 13 and generate corresponding first and second image sensor signals. The first sensor device is preferably configured to detect electromagnetic waves reflected in a first area 15 of the front side 12, while the second sensor device is configured to receive electromagnetic waves reflected in a second area 16 and / or a third area 17 of the rear side 13 to capture. For example, the first and second sensor devices can be designed as image sensors, in particular as cameras, which capture the corresponding areas 15-17. Alternatively, the first image sensor can also be designed to optically capture the entire front side 12 of the document of value 14 and to generate first image sensor data only on the basis of reflected electromagnetic waves captured in the first area 15. Accordingly, the second image sensor can be designed to optically detect the entire rear side 13 of the document of value 14 and only to generate second image sensor data based on reflected electromagnetic waves detected in the second area 16 and in the third area 17.

The position and / or size of the first, second and / or third area 15-17 is preferably selected so that there the value document has reflective properties which are characteristic of the denomination of the value document 14. For example, the print image of the document of value 14 has certain features 15'-17 'in the areas 15-17, in particular in the form of a number and / or a pattern, on the basis of which the denomination of the document of value 14 can be determined, for example whether it is a 5 or 10 euro banknotes.

In the example described, the first and second sensor data are image sensor data which - as in connection with Figure 1 already explained in more detail - written together in the storage device 9 of the first evaluation device 4 and linked there with one another in the classification of the value document 14. As a result, the classification of the value document 14 with regard to the denominations can be carried out solely by the first evaluation device 4.

Because the value document 14 can be classified in the first evaluation device on the basis of combined image sensor data, only one result of the classification, ie the denomination of the value document 14, needs to be transmitted to the central entity 7. Furthermore, in this case, the second evaluation device 5 for classifying the document of value 14 with regard to its denomination can be saved or used for a classification with regard to another class, such as, for example, soiling.

The above remarks on the in Figure 2 The example shown also apply accordingly to electromagnetic waves that are transmitted by the value document 14 and are each detected in the area of the front side 12 and rear side 13 by means of a sensor device. The statements also apply accordingly to ultrasound waves that are reflected and / or transmitted on the front and back of the document of value 14 and are each detected by means of a suitable sensor device.

Figure 3 shows an example of a value document 14, the properties of which are recorded with different types of sensors in different areas 15-17. In the present example, the properties are recorded with three different types of sensors in three different areas of the value document. Depending on the application, only two or more than three different types of sensors can be used.

The different types of sensors detect properties of the document of value 14 using different measurement principles. For example, in the present example it can be an image sensor, for example a camera, a dielectric or capacitive sensor, for example a capacitor, and an ultrasonic sensor, for example an array of piezoelectric elements. The sensors are preferably set up to detect the relevant properties of the document of value 14 in a spatially resolved manner, so that the correspondingly generated sensor data each correspond to an optical, capacitive or ultrasonic image of the three different areas 15-17.

The image sensor preferably detects an optical security feature 15 ″ of the value document 14 in the first area 15, for example a predetermined pattern. The dielectric or capacitive sensor detects in the second area 16 a dielectric security feature 16 ″ of the value document 14, for example a dielectric constant of a security strip. In the third area 17, the ultrasonic sensor detects a security feature 17 ″ of the value document 14 that can only be detected by means of ultrasonic waves, for example a varying thickness of the value document 14. These sensor data accordingly characterize the authenticity of the value document 14.

The sensor signals generated by the three different sensor types are written, for example, into the first memory device 9 of the first evaluation device 4 (see FIG Figure 1 , a third sensor device or a third sensor type is not shown there for reasons of clarity). As a result, they can be combined or jointly evaluated by the first evaluation device 4 in order to efficiently and reliably classify or check the value document 14 with regard to authenticity.

For example, the first evaluation device 4 can be designed to evaluate the image points of the images corresponding to the three different areas 15-17 with respect to one or more, in particular three, threshold values.

Because the value document 14 is classified in the first evaluation device 4 on the basis of merged sensor data, only one result of the classification, in the present example with regard to authenticity, of the value document 14 needs to be transmitted to the central entity 7. The instance 7 itself no longer needs to carry out any classification, but only controls the further processing, in particular sorting, of the value document depending on the determined class. A second evaluation device 5 or any other evaluation devices (in Figure 1 not shown) to classify the document of value 14 with regard to authenticity can be saved or used for classification with regard to another class, such as damage, soiling or limpness.

Claims (8)

1. An apparatus (1) for classifying value documents (14), in particular bank notes, having:

   - at least two sensor devices (2, 3) which are arranged to capture waves, in particular electromagnetic waves, reflected on a front side (12) and on a back side (13) of a value document (14) and to generate corresponding sensor data (8) or to capture properties of the value document (14) in at least two different regions (15-17) of the value document (14) by means of different measuring principles and to generate corresponding sensor data (8), and

   - at least one evaluation device (4, 5) which is arranged to classify the value document (14) with the aid of the sensor data (8) generated by the at least two sensor devices (2, 3), which sensor data relate to the waves reflected on the front side (12) and back side (13) of the value document (14) or to the properties of the value document (14) captured in the at least two different regions (15, 17) of the value document by means of different measuring principles, wherein the at least one evaluation device (4, 5) comprises a memory unit (9, 10) for data storage and a control device (6) is provided which is arranged to write the sensor data (8) generated by the at least two sensor devices (2, 3) into the memory unit (9, 10) of the at least one evaluation device (4, 5), wherein at least two evaluation devices (4, 5) respectively having a memory unit (9, 10) are provided and the control device (6) is arranged to write the sensor data (8) generated by the at least two sensor devices (2, 3) into each memory unit (9, 10) of the at least two evaluation devices (4, 5).
2. The apparatus (1) according to claim 1, wherein each of the at least two sensor devices (2, 3) have an evaluation device (4, 5) assigned thereto.
3. The apparatus (1) according to any of the above claims, wherein the sensor devices (2, 3) which are configured for capturing electromagnetic waves reflected from the front side (12) and back side (13) of the value document (14) comprise a first image sensor and a second image sensor, wherein the first image sensor is arranged to capture a remission image of the front side (12) of the value document (14) and to generate corresponding first image sensor data and the second image sensor is arranged to capture a remission image of the back side (13) of the value document (14) and to generate corresponding second image sensor data, and the evaluation device (4, 5) is arranged to classify the value document (14) with the aid of the first image sensor data and the second image sensor data.
4. The apparatus (1) according to claim 3, wherein the evaluation device (4, 5) is arranged to determine the denomination of the value document (14) with the aid of the first image sensor data and the second image sensor data.
5. The apparatus (1) according to claim 1 or 2, wherein the sensor devices (2, 3) which are configured for capturing properties of the value document (14) in at least two different regions (15-17) of the value document (14) by means of different measuring principles comprise at least two different sensor types of the following sensor types:

   - an optical sensor, in particular an image sensor, which is arranged to capture optical properties of the value document (14) and to generate corresponding sensor data (8),

   - an ultrasonic sensor which is arranged to capture reflection properties and/or transmission properties of the value document (14) for ultrasound and to generate corresponding sensor data (8),

   - a capacitive sensor which is arranged to capture dielectric properties of the value document (14) and to generate corresponding sensor data (8),

   - a magnetic sensor which is arranged to capture magnetic properties of the value document (14) and to generate corresponding sensor data (8), and the evaluation device (4, 5) is configured to classify the value document (14) with the aid of the sensor data (8) generated by the at least two different sensor types, which sensor data relate to properties of the value document (14) captured in the at least two different regions (15-17) of the value document (14).
6. The apparatus (1) according to claim 5, wherein the evaluation device (4, 5) is arranged to check the authenticity of the value document (14) with the aid of the sensor data (8) generated by the at least two different sensor types, which sensor data relate to properties of the value document (14) captured in the at least two different regions (15-17) of the value document (14).
7. A value-document processing system having

   - an apparatus (1) for classifying value documents (14) according to any of the above claims, and

   - a sorting apparatus which comprises different sorting pockets and is arranged to output the value documents (14) into the different sorting pockets in dependence on the classifications effected with the aid of the sensor data (8).
8. A method for classifying value documents (14) having the following steps:

   - capturing waves, in particular electromagnetic waves, reflected on a front side (12) and on a back side (13) of a value document (14) and generating corresponding sensor data (8) or capturing properties of the value document (14) in at least two different regions (15-17) of the value document (14) by means of different measuring principles and generating corresponding sensor data (8),

   - classifying the value document (14) with the aid of the generated sensor data (8) which relate to the waves reflected on the front side (12) and back side (13) of the value document (14) or to the properties of the value document (14) captured in the at least two different regions (15-17) of the value document (14) by means of different measuring principles,

   - writing the sensor data (8) generated for data storage by the at least two sensor devices (2, 3) into a memory unit (6) of the at least one evaluation device (4, 5), wherein at least two evaluation devices (4, 5) are provided which each have a memory unit (9, 10) and the sensor data (8) generated by the at least two sensor devices (2, 3) are written into each memory unit (9, 10) of the at least two evaluation devices (4, 5).

Images