ABBYY Development Inc.

Aspects of the disclosure provide for systems and methods for word shape-assisted searches in big data applications. The systems and methods of the disclosure enable operations that identify a mapping scheme in which words are represented via word shapes with same word shapes capable of representing different words. Operations further include forming hypotheses that prospectively associate words in a document with target entries in a database, and eliminainge at least some of the formed hypotheses based on mismatch between sets of word shapes corresponding to the words of the formed hypotheses and word shapes of various database entries.

An example method of processing images of deformed indicia-bearing surfaces includes: detecting, within a document image, a plurality of image fragments, wherein each image fragment of the plurality of image fragment contains a respective sequence of alphabet symbols; grouping the plurality of image fragments by lines of text to be reconstructed in the document image; generating a map of isolines associated with the document image, wherein an isoline identifies a set of points that lie on a straight line of an undistorted image corresponding to the document image; generating a reverse transformation matrix that defines a set of transformations to be applied to the document image in order to remove image distortions caused by deformations of an indicia bearing surface; and generating an undistorted document image by applying the reverse transformation matrix to the document image.

Systems and methods are disclosed to receive a training data set comprising a plurality of document images, wherein each document image of the plurality of document images is associated with respective metadata identifying a document field containing a variable text; generate, by processing the plurality of document images, a first heat map represented by a data structure comprising a plurality of heat map elements corresponding to a plurality of document image pixels, wherein each heat map element stores a counter of a number of document images in which the document field contains a document image pixel associated with the heat map element; receive an input document image; and identify, within the input document image, a candidate region comprising the document field, wherein the candidate region comprises a plurality of input document image pixels corresponding to heat map elements satisfying a threshold condition.

Aspects and implementations provide for mechanisms of detection and decoding of barcodes in images. The disclosed techniques include estimating dimensions of a module of a barcode based on geometric characteristics of a barcode image, forming hypotheses that group modules into barcode symbols, and assessing viability of formed hypotheses. Various operations of the techniques may involve the use of neural networks, including estimation of module dimensions and assessment of groupings of modules into lines and lines into barcode symbols. The techniques may be used for decoding of barcodes captured in images of unfavorable conditions, including blur, perspective, sub-optimal lighting, barcode deformation, and the like. The techniques may be applied to decoding linear one-dimensional barcodes, two-dimensional barcodes, and stacked linear barcodes.

Aspects and implementations provide for mechanisms of detection and decoding of barcodes in images. The disclosed techniques include estimating dimensions of a module of a barcode based on geometric characteristics of a barcode image, forming hypotheses that group modules into barcode symbols, and assessing viability of formed hypotheses. Various operations of the techniques may involve the use of neural networks, including estimation of module dimensions and assessment of groupings of modules into lines and lines into barcode symbols. The techniques may be used for decoding of barcodes captured in images of unfavorable conditions, including blur, perspective, sub-optimal lighting, barcode deformation, and the like. The techniques may be applied to decoding linear one-dimensional barcodes, two-dimensional barcodes, and stacked linear barcodes.

Aspects and implementations provide for techniques of fast and efficient detection of depictions in multi-page documents and documents having complex structure. The disclosed techniques include processing an image of a document to generate probability distributions (PDs) predicting reference features (RFs) of the document. The model is trained using a first PD-to-RF mapping that samples RFs using training PDs generated for a training image. The techniques further include predicting the RFs using a second PD-to-RF mapping that determines the RFs based characteristics of the individual PDs. The techniques further include generating, using the predicted of RFs, a corrected image of the document, and extracting, using the corrected image, a content of the document.

Aspects of the disclosure provide for mechanisms for identification of text fields in documents using neural networks. A method of the disclosure includes obtaining vectors, representative of objects in a document and processing the vectors to generate key hypotheses associating key(s) with one or more objects and value hypotheses associating value(s) with zero or more objects. The method further includes generating key-value association (KVA) hypotheses associating a selected key hypothesis with a selected value hypothesis and characterized by a KVA likelihood score that is based on at least a key likelihood score associated with the selected key hypothesis and a value likelihood score associated with the selected value hypothesis. The method further includes identifying one or more target KVAs of the document using the KVA likelihood scores of the generated KVA hypotheses.

Techniques are disclosed for receiving, from one or more data sources, event-related data for a set of event sequences; selecting one or more event grouping criteria from a list of event grouping criteria, wherein the list of event grouping criteria comprises a criterion of grouping by an event location, a criterion of grouping by an event entity, and a criterion of grouping by an event time; grouping, into one or more groups, event sequences within the set of event sequences based on the one or more event grouping criteria; calculating sequence metrics for each group of the one or more groups of the event sequences within the set of event sequences; and displaying, on a user interface, the sequence metrics for the set of event sequences.

Aspects of the disclosure provide for mechanisms for identification of objects in images using neural networks. A method of the disclosure includes: obtaining an image, representing each element of a plurality of elements of the image via an input vector of a plurality of input vectors, each input vector having one or more parameters pertaining to visual appearance of a respective element of the image, providing the plurality of input vectors to a first subnetwork of a neural network to obtain a plurality of output vectors, wherein each of the plurality of output vectors is associated with an element of the image, identifying, based on the plurality of output vectors, a sub-plurality of elements of the image as belonging to the image of the object, and determining, based on locations of the sub-plurality of elements, a location of an image of an object within the image.

A method of detecting fields in document images includes: receiving, by a processing device, a codebook comprising a set of visual words, each visual word corresponding to a center of a cluster of local descriptors, wherein each local descriptor is associated with a respective keypoint region of a first set of document images; calculating, based on a second set of document images, for each visual word of the codebook, a respective frequency distribution of a field position of a specified field with respect to the visual word; loading a document image for extraction of target fields; and detecting fields in the document image based on the calculated frequency distributions.