Abbyy Development Inc.

Yuri Chulinin

Dmitry Deryagin

Mikhail Atroshchenko

Oleg Senkevich

Atroshchenko Mikhail Yurievich

Yury Vatlin

The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed create and store a decision tree, the nodes of which include classifiers that each recognizes the symbol that corresponds to a symbol image. Input of a symbol image to the decision tree and processing of the symbol image through one or more nodes of the decision tree returns a symbol corresponding to the symbol image.

Methods and systems for decision-tree-based automated symbol recognition

The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed carry out an initial processing step on one or more scanned images to identify a subset of the total number of symbols frequently used in the scanned document image or images. One or more lists of graphemes for the language of the text are then ordered in most-likely-occurring to least-likely-occurring order to facilitate a second optical-character-recognition step in which symbol images extracted from the one or more scanned-document images are associated with one or more graphemes most likely to correspond to the scanned symbol image.

Methods and systems for efficient automated symbol recognition

Disclosed are systems, computer-readable mediums, and methods for determining that text contains Chinese, Japanese, or Korean characters. One method includes determining a language hypothesis for each text fragment in a plurality of text fragments identified from connected components in a document image. The method further includes selecting a first subset of text fragments from the plurality of text fragments based on ratings for the language hypothesis of each text fragment in the plurality of text fragments. The method further includes verifying, by a processor, the language hypothesis of one or more text fragments in the first subset of text fragments based on optical character recognition of the one or more text fragments. The method further includes determining, by the processor, that Chinese, Japanese, or Korean (CJK) characters are present in the document image based on the verification of the language hypothesis of each of the one or more text fragments.

Chinese, Japanese, or Korean language detection

The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed carry out an initial processing step on one or more scanned images to identify, for each symbol image within a scanned document, a set of graphemes that match, with high frequency, symbol patterns that, in turn, match the symbol image. The set of graphemes identified for a symbol image is associated with the symbol image as a set of candidate graphemes for the symbol image. The set of candidate graphemes are then used, in one or more subsequent steps, to associate each symbol image with a most likely corresponding symbol code.

Methods and systems for efficient automated symbol recognition using multiple clusters of symbol patterns

Disclosed are systems, computer-readable mediums, and methods for determining a text contains Chinese, Japanese, or Korean characters. A document image is received and binarized. The binarized document image is searched for connected components. A plurality of fragments is identified based on the connected components. A language hypothesis for each fragment of the plurality of fragments is determined. The language hypothesis has a probability rating. A subset of fragments from the plurality of fragments having the highest probability ratings is selected. The language hypothesis of each fragment in the subset of fragments is verified. A determination of the presence of Chinese, Japanese, or Korean characters is made based at least on the verification of the language hypothesis of the subset of fragments.

The current application is directed to a method and system for automatically determining the sense orientation of regions of scanned-document images that include symbols and characters of languages that are not written as simple sequential strings of alphabetic characters. In one implementation, the sense-orientation method and system to which the current application is directed employs a relatively small set of orientation-marker characters that occur frequently in printed text and that lack rotational symmetry. In this implementation, text-character images within a region of a scanned-document image are compared to each of a set of orientation-marker patterns corresponding to orientation-marker characters in order to identify images corresponding to orientation-marker patterns in the text-containing region of the scanned-document image and to determine an overall sense orientation for the text-containing region of the scanned-document image based on the orientations of the identified orientation-marker patterns.

Method and system for text-image orientation

A method for detecting a junction in a received image of the line of text to update a junction list with descriptive data is provided. The method includes creating a color histogram based on a number of color pixels in the received image of the line of text and detecting, based at least in part on the received image of the line of text, a rung within the received image of the line of text. The method also includes identifying a horizontal position of the detected rung in the received image of the line of text and identifying a gateway on the color histogram, wherein the identified gateway is associated with the detected rung. The junction list is updated with data including a description of the identified gateway.

Detecting a junction in a text line of CJK characters

Methods are described for determining an optimal path for creating a scheme for dividing a text line of Chinese, Japanese or Korean (CJK) characters into character cells prior to applying classifiers and recognizing characters. Gaps between characters are found as a window is moved down the text line. Finding gaps may involve finding 4-connected paths. A histogram is built based on distances from start of window to a respective gap. The window is moved to the end of each gap after each gap is found and distances measured. Process is repeated until window reaches the end of the text line and all gaps found. A linear division graph (LDG) is constructed according to detected gaps. Penalties for certain distances are applied. An optimum path is one with a minimal penalty sum and can be used as a scheme for dividing text lines into character cells.

Fast CJK character recognition

A method is described for creating a scheme for dividing a text line of Chinese, Japanese or Korean (CJK) characters into character cells prior to applying classifiers and recognizing individual characters. Gaps between characters are found as a window is moved down the length of a text line. A histogram is built based on distances from the start of the window to a respective gap as the window is moved. The window is moved to the end of each gap after each gap is found and distances measured. This is repeated until the window reaches the end of the text line. A linear division graph (LDG) is constructed according to the detected gaps. Penalties for certain distances are applied. An optimum path is one with a minimal penalty sum and can be used as a scheme for dividing a text line into character cells.

Growing community of inventors

Moscow, Russia

Yuri Chulinin