Abstract: An image processing method includes recognizing a first object that is included in the image data, calculating a positional variation amount of a feature point that corresponds to the first object and is moving in an image center direction so as to calculate a moving speed of the first object on the basis of the positional variation amount, determining whether or not the first object is a gaze target object of the user, in accordance with a behavior of the first object, the behavior being obtained on the basis of the positional variation amount of the first object among the plurality of image data, of which acquisition time is respectively different and whether or not the object continuingly exists in a second region, the second region being positioned in an inside of the first region and including a center point of the image data, for a predetermined period of time.

Abstract: An information processing apparatus includes an image capturing section to capture an image of a hand; an extracting section to extract a hand area from the captured image; a reference line determining section to determine a reference pushdown line in the image on the hand area; a determining section to determine a pushdown move if the bottom part of the hand area comes below the reference pushdown line; a first position determining section to determine a depth position based on an aspect ratio of the hand area if the pushdown move is determined; a second position determining section to determine a lateral position based on a position of the bottom part of the hand area if the pushdown move is determined; and an input key determining section to determine an input key from the determined depth position and lateral position.

Abstract: An image processing device that accesses a storage unit that stores a feature point of a recognition-target object, the device includes an obtaining unit mounted with a user and configured to obtain image data in a direction of a field of view of the user; a recognizing unit configured to recognize the recognition-target object included in the image data by extracting a feature point from the image data and associating the extracted feature point and the feature point of the recognition-target object stored in the storage unit with each other; a calculating unit configured to calculate a location change amount of the feature point corresponding to the recognition-target object recognized by the recognizing unit from a plurality of the image data obtained at different times and calculate a motion vector of the recognition-target object from the location change amount; and a determining unit configured to determine a movement.

Abstract: An information processing apparatus includes an image capturing section to capture an image of a hand; an extracting section to extract a hand area from the captured image; a reference line determining section to determine a reference pushdown line in the image on the hand area; a determining section to determine a pushdown move if the bottom part of the hand area comes below the reference pushdown line; a first position determining section to determine a depth position based on an aspect ratio of the hand area if the pushdown move is determined; a second position determining section to determine a lateral position based on a position of the bottom part of the hand area if the pushdown move is determined; and an input key determining section to determine an input key from the determined depth position and lateral position.

Abstract: An image processing method includes recognizing a first object that is included in the image data, calculating a positional variation amount of a feature point that corresponds to the first object and is moving in an image center direction so as to calculate a moving speed of the first object on the basis of the positional variation amount, determining whether or not the first object is a gaze target object of the user, in accordance with a behavior of the first object, the behavior being obtained on the basis of the positional variation amount of the first object among the plurality of image data, of which acquisition time is respectively different and whether or not the object continuingly exists in a second region, the second region being positioned in an inside of the first region and including a center point of the image data, for a predetermined period of time.

Abstract: A character input method to be executed by a computer, the character input method includes: acquiring a first image from an imaging device; detecting an object from the first image; specifying a character group corresponding to a first position of the object detected from the first image, based on correspondence information in which each of a plurality of character groups including a plurality of characters is associated with each of a plurality of regions set for the first image; acquiring a second image acquired from the imaging device at a time different from a time at which the first image is acquired; detecting the object from the second image; and designating one character from the specified character group, based on a second position of the object detected from the second image.

Abstract: According to an aspect of an embodiment, a method of detecting boundary line information contained in image information comprising a plurality of pixels in either one of first and second states, comprising: detecting a first group of pixels in the first state disposed continuously in said image information to determine first line information and detecting a second group of pixels in the first state disposed adjacently with each other and surrounded by pixels in the second state to determine edge information based on the contour of the second group of pixels; and determining the boundary line information on the basis of the information of the relation of relative position of the line information and the edge information and the size of the first and second group of pixels.

Abstract: A program causes a computer to function as a document recognition apparatus, having an extraction unit for extracting connected components of pixels from an input image, a generation unit for generating a reference element that is connected components of pixels extracted by the extraction unit and combined elements obtained by combining the reference element and connected components of pixels adjacent to the reference element as an element to be estimated, a calculation unit for calculating a degree of certainty that indicates how much the element to be estimated generated by the generation unit seems to be a character, and a determination unit for identifying elements that seem to be characters among the elements to be estimated based on the degree of certainty calculated by the calculation unit.

Abstract: An image recognition apparatus recognizes the correspondence between character strings and logical elements composing a logical structure in an image in which the character strings are described as the logical elements to recognize each logical element.

Abstract: A character area extracting device includes a reflective and non-reflective area separation unit separating image data into reflective and non-reflective areas, and binarizing the image data by changing a first threshold value when it is inappropriate; a reflective area binarizing unit separating the reflective area into character and background areas, and binarizing it by changing a second threshold value when it is inappropriate; a non-reflective area binarizing unit separating the non-reflective area into the character and background areas, and binarizing it by changing a third threshold value when it is inappropriate; a reflective and non-reflective area separation evaluation unit; and a line extracting unit connecting the character areas of the reflective and non-reflective areas and extracting positional information of the connected character areas in the image data.

Abstract: The form data extracting apparatus, even input form does not have a logical structure stored in the generic logical structure DB, by using logical elements in the existing logical structure and a registered form obtained on the basis of (a) the logical structure, (b) pieces of position information of the logical elements, and (c) a relation between the logical elements. A logical element and a logical structure are extracted from the input form, and the extracted logical structure can be defined as a new registered form or a new logical structure.

Abstract: A dictionary creating apparatus registers probability distributions each including an average vector and a covariance matrix, in a dictionary. The dictionary creating apparatus organizes plural distribution profiles of character categories having similar feature vectors into one typical distribution profile, and registers the typical distribution profile and the character categories to be organized, associated with each other, in the dictionary, without registering eigenvalues and eigenvectors of all character categories, associated with each other, in the dictionary.

Abstract: An area extraction method including obtaining a character lattice showing a connection relation between unit areas, which are obtained by separating a character string pattern in an image into patterns each recognized as corresponding to a single character, judging whether or not all combinations of each of the unit areas in the obtained character lattice and each of the unit areas in a regular lattice defining a regular connection relation between the unit areas are likely to be established, generating a path coupling between nodes corresponding to the combination of the unit areas which is determined as likely to be established, determining an optimum path from the generated paths based on a degree of coincidence with the regular lattice or the character lattice, and extracting from an image the unit areas in the character lattice corresponding to the determined optimum path.

Abstract: A document type identifying apparatus includes in advance a database storing therein keywords used as keys that identify document types in association with each document type. The document type identifying apparatus aligns word strings written on a document and generates partial keyword strings for each keyword by using the keywords stored in the database. The partial keyword strings are to be checked for matching with the word strings written on the document. Then, the document type identifying apparatus checks matching of the grouped and aligned word strings with the partial keyword strings and obtains, for each keyword, each number of matched words with the highest matching rates between the grouped word strings that are successfully matched and the partial keyword strings. Then, each number of matched words is used to calculate each evaluation value to determine the document type.

Abstract: This method includes: extracting a feature vector for an input character from a reading result of the input character; calculating distances between the feature vector for the input character and vectors including average vectors stored in a system dictionary storing, for each character, the average vector and distribution information, and feature vectors stored in a user dictionary; extracting the top N character codes in an ascending order of the calculated distances; obtaining second distribution information for the character codes, which are included the user dictionary and in the top N character codes; calculating, for each of the top N character codes, a second distance with the feature vector for the input character, by using, for the character codes, which are included in the user dictionary and in the top N character codes, the second distribution information; and identifying a character code whose second distance is shortest.

Abstract: A method for assisting in the creation of a logical structure model, which stores, from an image in which character strings associated respectively with a plurality of logical elements constituting a logical structure are described, the logical elements, character strings associated with the logical elements, and the logical structure, wherein character strings in an input image and the logical structure among the character strings in the input image are extracted, a logical element is selected among the plurality of logical elements according to the degrees of similarity between the extracted character strings and the character string associated respectively with the plurality of logical elements stored in the logical structure model, a character string associated with the selected logical element and a character string in the input image associated with the logical element based on the logical structure among the extracted character strings in the input image are extracted.

Abstract: An image recognition method is conducted by recognizing logical elements based on a logical structure model set to correspond to the logical structure of an image of individual character strings, collecting information processed with the logical structure model of images of a logical structure, acquiring a recognition result when recognizing an image of a logical structure by processing information collected with a post-update logical structure model, and outputting warning information about the post-update logical structure model to an output unit when a result of the comparison is a non-match.

Abstract: According to an aspect of an embodiment, an apparatus for analyzing and determining correlation of information contained in a given form containing blocks, at least one of the blocks containing data indicative of a header, the rest of the blocks containing data in association with header information, comprising: a memory for storing templates having nodes, character data associated with said nodes respectively, and relative position information between said nodes; and a processor for analyzing and determining correlation of the information according to a process comprising: obtaining data contained in said blocks in the given form, determining relative position of said blocks to produce relative position information, analyzing the data obtained from the blocks and the relative position information of the blocks in comparison with the character data and the relative position information of said nodes of said templates, and determining correlation of the data contained in said blocks.

Abstract: This invention provides a correcting device and a correcting method for perspective transformation of document images.

Abstract: A form processing program which is capable of automatically extracting keywords. When the image of a scanned form is entered, a layout recognizer extracts a readout region of the form image, a character recognizer recognizes characters within the readout region. A form logical definition database stores form logical definitions defining strings as keywords according to logical structures which are common to forms of same type. A possible string extractor extracts as possible strings combinations of recognized characters each of which satisfies defined relationships of a string. A linking unit links the possible strings according to positional relationships, and determines a combination of possible strings as keywords.