In one implementation, a processor: (1) receives an image of a candidate mark from an image acquisition device, (2) uses the image to measure one or more characteristics at a plurality of locations on the candidate mark, resulting in a first set of metrics, (3) removes, from the first set of metrics, a metric having a dominant amplitude, resulting in a trimmed first set of metrics, (4) retrieves, from a computer-readable memory, a second set of metrics that represents one or more characteristics measured at a plurality of locations on an original mark, (5) removes, from the second set of metrics, a metric corresponding to the metric removed from the first set of metrics, resulting in a trimmed second set of metrics, (6) compares the trimmed first set of metrics with the trimmed second set of metrics, and (7) determines whether the candidate mark is genuine based on the comparison.

A currency classification device that classifies currency types using currency images includes a feature value calculator, a storage, and an output unit. The feature value calculator calculates feature values for every currency type that is a candidate for classification from an image area common in images of every currency type. The storage stores the feature values calculated by the feature value calculator from learning images, which are currency models, as templates for every currency type. The output unit outputs the currency type corresponding to the template having a highest value of similarity with the feature value calculated by the feature value calculator an input image, which is a currency image subject to classification, in the templates stored in the storage as a classification result.

An identification device includes: an observation object shape frame display configured to display, on a display screen, an observation object shape image indicating a shape of an anti-counterfeit medium observed at an observation angle, and display image data that is an image of an imaging object of an image-capturing device, the anti-counterfeit medium being designed such that an observed pattern of light varies as the observation angle varies; a shape similarity calculator configured to calculate a shape similarity between the observation object shape image and an outer shape of the anti-counterfeit medium; and an imaging determinator configured to perform imaging determination as to whether the observation angle and an observation position of the image-capturing device are correct based on whether the shape similarity is equal to or greater than a shape similarity threshold.

A method and a device for adaptively recognizing a value document are provided. The method includes: acquiring a collection parameter, and collecting a photoelectric signal of the value document; acquiring a photoelectric signal correction amount, and performing digital compensation on the photoelectric signal; performing feature extraction on the photoelectric signal subjected to the digital compensation to obtain a feature vector; inputting the feature vector to a preset classifier for recognition, to obtain a recognition result of the value document; acquiring a specific region on the value document; acquiring feature information of the photoelectric signal of the value document; calculating an accumulation component and a differential error of the value document; calculating a total correction amount of the photoelectric signal; updating the photoelectric signal correction amount and the collection parameter; and outputting the recognition result.

A system and method for automatic identification of photocopied documents is disclosed wherein the method is performed by capturing an image of a marked printed document; decoding a digital watermark embedded in the image, obtaining a mark identifier; recovering, by searching a database, at least one calibration parameter associated with the mark identifier; applying a discrete Fourier transform to the image, obtaining a frequency matrix; obtaining at least one maximum frequency value in the frequency matrix; comparing the at least one maximum frequency value with at least one calibration parameter; determining, on the basis of the comparison, if the marked printed document is an original document or a photocopied document.

An image of a check is captured by an imaging device and processing of the digital image of the check for deposit at a remote server may be accomplished with a downloaded software application on a portable computing device associated with the imaging device. The downloaded application may include one or more trained machine learning models for processing the captured image. The portable computing device may utilize deterministic algorithms for certain image processing tasks and machine learning models for others. The selection between machine learning and deterministic processing may be made locally on the portable device or in response to instructions from an institution server to use a particular processing method.

A security element comprising a first and a second pattern formed in or on a substrate is described, the first pattern (105; 205) being formed by discrete elements (105a-105g; 205a-205c) of a first material that are distributed over a first region (101) of the substrate (100; 200), the second pattern (106; 206) being formed by discrete elements (106a-106i; 206a-206c) of a second material that are distributed over a second region (102) of the substrate (100; 200), said second material being different from said first material, said first and second regions of the substrate overlapping, wherein the discrete elements of at least one of the first and second patterns are distributed randomly, a part of the discrete elements of the first pattern (105; 205) overlap with a part of the discrete elements of said second pattern (106; 206), and the security element is defined by the first pattern (105; 205), the second pattern (106; 206) and a third pattern (107; 207) associated with the overlap of some or all of the discrete elements of said first and second patterns.

The invention relates to a method for authenticating an illustration, comprisingencoding a message in the form of a two-dimensional barcode comprising blocks, each block coding a fragment of said message and comprising a set of coding sub-blocks, each sub-block comprising a set of binary elements. It is essentially characterised in that the encoding comprises prior steps consisting in:defining or identifying a set of noteworthy points in the illustration,calculating a set of attributes depending on certain at least of the noteworthy points,selecting, among the calculated attributes, at least one attribute allowing a digital fingerprint to be definedoptionally compressing said digital fingerprint,optionally signing said digital fingerprint by means of a cryptographic signature, andrecording in the message one among:a set of at least one attribute,the digital fingerprint,the compressed digital fingerprint, andthe signed and optionally compressed digital fingerprint.

In one implementation, a processor: (1) receives an image of a candidate mark from an image acquisition device, (2) uses the image to measure one or more characteristics at a plurality of locations on the candidate mark, resulting in a first set of metrics, (3) removes, from the first set of metrics, a metric having a dominant amplitude, resulting in a trimmed first set of metrics, (4) retrieves, from a computer-readable memory, a second set of metrics that represents one or more characteristics measured at a plurality of locations on an original mark, (5) removes, from the second set of metrics, a metric corresponding to the metric removed from the first set of metrics, resulting in a trimmed second set of metrics, (6) compares the trimmed first set of metrics with the trimmed second set of metrics, and (7) determines whether the candidate mark is genuine based on the comparison.

A method of determining whether a user of a mobile device corresponds to a previously authenticated user. The method comprises: acquiring a first image from the identity document, the first image being a photographic image and or a digital image; causing a camera connected to or integral with the mobile device to capture a second image, the second image corresponding to a user of the mobile device; comparing data indicative of the first image and data indicative of the second image, whereby to determine whether the first image and the second image represent the same user; and responsive to determining that the first image and the second image represent the same user, forming an association between the previously authenticated user and the mobile device.