The invention relates to a method for authenticating an optically variable security element (1), in particular a diffractive security element, with the steps: a) capturing an image sequence with at least one individual image of the security element (1) by means of a sensor (31), in particular a hand-held device (3), preferably a smartphone, tablet or a PDA; b) checking whether at least one predetermined item of optical information is present in at least one individual image of the image sequence.

A method for supplying measuring data of a value-document processing apparatus for processing value documents of stipulated different processing types, has a sensor device, a control device, and a display device. Data sets are read, which respectively contain, for at least two of the processing types, processing-type data by means of which the processing types can be distinguished and the number of the value documents of the respective processing type that are to be fed to the value-document processing apparatus, and display data for actuating the display device are so established from the data sets that, upon actuation with the display data, the display device displays the processing types and the numbers of the value documents. The display device is actuated with the display data, and measuring data are respectively captured by means of the sensor device in accordance with the displayed processing types.

A computerized system for classifying and authenticating documents is provided. The Classification process involves the creation of a Unique Pair Feature Vector which provides the best discrimination information for each pair of Document Classes at every node in a Pairwise Comparison Nodal Network. The Nodal Network has a plurality of nodes, each node corresponding to the best discrimination information between two potential document classes. By performing a pairwise comparison of the potential documents using this nodal network, the document is classified. After classification, the document can be authenticated for validity.

A method for compressing a bi-level document image containing text is disclosed. The document image is segmented into symbol images each representing a letter, numeral, etc. in the document. The symbol images are classified into a plurality of classes, each class being associated with a template image and a class index. Classification is done by comparing each symbol to be classified with template of existing classes, using a number of image features including zoning profiles, side profiles, topology statistics, and low-order image moments. These image features are compared using a tolerance based method to determine whether the symbol matches the template. After classification, certain classes that have few symbols classified into them may be merged with other classes. In addition, the template images of the classes are down-sampled, where the final sizes of the template images are dependent on the likelihood of confusion of the template with other templates.

A bill recognizing and counting apparatus includes an operation unit that receives setting of bill processing modes including a denomination mode, a counting mode, a different-denomination recognition mode, and an authenticity determination mode; a feeding and transporting mechanism; and a control unit that performs control for changing a processing speed according to the bill processing mode. When the bill processing mode is in the counting mode, the different-denomination recognition mode, or the authenticity determination mode, the control unit increases the processing speed by setting the feeding and transporting mechanism to a higher speed than the speed set in the denomination mode. The increase in speed is in accordance with a reduced time necessary to process a reduced amount of data associated with the denomination mode.

A system comprising: a check Image Record (CIR) database configured to store, for each of a plurality of accounts, a CIR, wherein each CIR comprises feature information related to features extracted from a plurality of reference checks associated with the associated account of the plurality of accounts; memory configured to store instructions; and a processor coupled with the CIR database and the memory, the processor configured to run the instructions, which cause the processor to: receive an image of a test check associated with an account of the plurality of accounts, extract feature information from the image, compare the features with the feature information stored in the CIR database for the account associated with the test check, generate a fraud score, and update each CIR by determining.

Recognizing magnetic ink characters in an automated teller machine and, more particularly, recognizing magnetic ink characters in an automated teller machine. Results of optical character recognition (OCR) are compared based on an image acquired through a contact image sensor (CIS) provided in an authentication unit and character-based waveforms of magnetic ink characters acquired through an MR sensor. Whether a bill is legitimate is authenticated, and thus correct reading of magnetic ink characters printed on a check is realized. The structure of the authentication unit can be simplified so that correct recognition of the magnetic ink characters printed on the check in a normal automated teller machine is supported without a high-resolution MICR sensor, and the cost of manufacturing the automated teller machine can be effectively reduced.

A paper sheet handling apparatus includes: a displacement amount detector that includes a pressing part intended to press a paper sheet against a transporting face of a paper sheet transporting path and having an initial position at which the pressing part is not in contact with the transporting face of the paper sheet transporting path, the displacement amount detector detecting a displacement amount of displacement of the pressing part from the initial position in a direction perpendicular to the transporting face, the pressing part being displaced according to a thickness of a paper sheet passing between the transporting face and the pressing part; a reference displacement amount storage; a paper sheet thickness storage; and a tape thickness threshold storage.

A system comprising: a check Image Record (CIR) database configured to store, for each of a plurality of accounts, a CIR, wherein each CIR comprises feature information related to features extracted from a plurality of reference checks associated with the associated account of the plurality of accounts; memory configured to store instructions; and a processor coupled with the CIR database and the memory, the processor configured to run the instructions, which cause the processor to: receive an image of a test check associated with an account of the plurality of accounts, extract feature information from the image, compare the features with the feature information stored in the CIR database for the account associated with the test check, generate a fraud score, and update each CIR by determining.

A method for generating synthetic banknotes requires that a multispectral image be generated from a sample banknote. The multispectral image is processed to create a training image in a two-dimensional space. A generative adversarial network is trained using the training image. Synthetic banknotes are generated by seeding the trained generative adversarial network with random data. The synthetic banknotes may then be used to generate a banknote template for a currency validator.