Abstract: A wordspotting system and method are disclosed for processing candidate word images extracted from handwritten documents. In response to a user inputting a selected query string, such as a word to be searched in one or more of the handwritten documents, the system automatically generates at least one computer-generated image based on the query string in a selected font or fonts. A model is trained on the computer-generated image(s) and is thereafter used in the scoring the candidate handwritten word images. The candidate or candidates with the highest scores and/or documents containing them can be presented to the user, tagged, or otherwise processed differently from other candidate word images/documents.

Abstract: Conventionally, there is the problem that a source program that is to be converted cannot be properly analyzed and the conversion ratio cannot be improved.

Abstract: Methods and system for providing vision assistance using a portable telephone with a built-in camera. In some embodiments, the system identifies the value of a bank note by determining the average number of transitions between black and white in each vertical line of pixels corresponding to a numeric digit. In other embodiments, the system captures an image and identifies an object in the image by comparing the value of each pixel in the image to a threshold intensity and marking the pixels that exceed the threshold. The system then generates a plurality of candidate groups by grouping marked pixels that are within a predetermined distance from other marked pixels. The object is identified based on the relative position of each candidate group to other candidate groups.

Abstract: An image processing device is provided which generates an easily reusable electronic document from an input image in which different page sizes are mixed. The image processing device generates a plurality of pieces of display information from a plurality of document images, and, depending on the size and the direction of each of the images, converts the pieces of display information into electronic documents. That is, the plurality of pieces of display information are divided into a plurality of groups, depending on the size and the direction of each of the images, and the display information included in each of the groups is converted into a separate electronic document. Further, sequence information based on the input order of the plurality of document images is stored on an electronic document.

Abstract: The transfer of a duplicate electronic document between image forming devices is done with an electronic document that is formed of only resolution-independent vector data and the like, and a normal printing of the duplicate electronic document or printing of different resolution is performed by developing the vector data. In high-quality printing of the duplicate electronic document, a Fill Map included in the original document the information indicating the location of an electronic document of copy source that is embedded in a metadata specifies is obtained, and this printing is made using the Fill Map.

Abstract: The described implementations relate to assisted face recognition tagging of digital images, and specifically to context-driven assisted face recognition tagging. In one case, context-driven assisted face recognition tagging (CDAFRT) tools can access face images associated with a photo gallery. The CDAFRT tools can perform context-driven face recognition to identify individual face images at a specified probability. In such a configuration, the probability that the individual face images are correctly identified can be higher than attempting to identify individual face images in isolation.

Abstract: An object of this invention is to allow a user to easily and simply designate or input an image serving as a document search key. That is, a search apparatus reads a document image (S7001) to obtain image data, extracts an image region in the image data (S7004), and displays, on display means, a list of images corresponding to the extracted image regions (S7008). When a user selects at least one of the images displayed in the list via an input means (S7009), the search is executed by using the selected image as a search key (S7010).

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: An image document processing device extracts a character sequence image having M number of characters in an image document, divides the image into individual character images, extracts features of the individual character images, and based on the features, selects N (N is an integer more than 1) character images in the order of degree of matching from a font-feature dictionary for storing features of all character images according to fonts, and generates an M×N index matrix for the extracted character sequence. In searching, the device searches an index-information storage section with respect to each search character included in a search keyword in an input search expression, and extracts an image document including an index matrix including the search keyword. This provides an image document processing device and an image document processing method each allowing indexing not requiring user's operation and each allowing highly precise searching without OCR recognition.

Abstract: A headline-region initial processing section clips a headline-region image in an image document, divides the image into individual character images, and extracts features of the individual character images. Based on the features, a candidate-character-sequence generating section selects N (N is an integer more than 1) character images as candidate characters in the order of degree of matching from a font-feature dictionary for storing features of individual character images, and generates M×N index matrix where M is the number of characters in an extracted character sequence. Based on the index matrix, a document-name generating section generates a meaningful document name according to the image document. An image-document-DB management section manages accumulated image documents using the document name.

Abstract: The maximum number of scaled images formed for one document and the scaling ratio set for each of scaled images are accepted by an operation panel, the basic scaling ratio is read from a table defining the scaled image arrangement information and the like, the scaling ratio of the original image data obtained by an image reading section is changed, and scaled images laid out on one sheet are generated. The generated plurality of scaled images are arranged according to the arrangement information defined by the table, and image formation is performed by an image forming section, thereby obtaining a multi-shot copy in which a plurality of images of different scaling ratio are laid out on one sheet.

Abstract: A processing device may recognize a number of input handwritten strokes, which may represent a mathematical expression, a chemical formula, or other two-dimensional structure. Rewriting rules of a grammar may be applied to the strokes to produce a number of possible recognition results. Each of the possible recognition results has a respective score based on a sum of rewriting rules applied to the strokes to produce respective ones of the possible recognition results. Input may be provided to identify misrecognized strokes and a correct terminal production, or symbol corresponding to the misrecognized strokes. Strokes may be misrecognized for many reasons, including parsing errors, over-grouping or under-grouping of matrices, and improper placement of a recognized terminal production, or symbol, with respect to a root structure. Correction hints may be leveraged for correcting types of errors mentioned above.

Abstract: A document processing apparatus includes: a character segmentation unit that segment a plurality of character images from a document image; a character image classifying unit that classifies the character images to categories corresponding to each of the character images; an average character image obtaining unit that obtains average character images for each of the categories of the character images classified by the character image classifying unit; a character recognizing unit that performs a character recognition to a character contained in each of the average character images; and an output unit that outputs character discriminating information as a character recognition result obtained by the character recognizing unit.

Abstract: An information processing apparatus according to one aspect of the present invention includes a area recognizing unit to recognize, with respect to areas specified in predetermined representations within image data, a first area specified in a first area specifying representation and a second area specified in a second area specifying representation different from the first area specifying representation, a position information acquiring unit to acquire position information of the first area, which is recognized by the area recognizing unit as the position information for specifying a character recognition target area within the image data and a name-of-item acquiring unit to acquire character information obtained by recognizing characters existing in the second area recognized by the area recognizing unit as a name of item with respect to the character recognition target area specified by the position information acquired by the position information acquiring unit.

Abstract: Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.

Abstract: An interactive system provides for increasing retrieval performance of images depicting text by allowing users to provide relevance feedback on words contained in the images. The system includes a user interface through which the user queries the system with query terms for images contained in the system. Word image suggestions are displayed to the user through the user interface, where each word image suggestion contains the same or slightly variant text as recognized from the word image by the system than the particular query terms. Word image suggestions can be included in the system by the user to increase system recall of images for the one or more query terms and can be excluded from the system by the user to increase precision of image retrieval results for particular query terms.

Abstract: An image processing method includes receiving an image including a writing, detecting a position of the writing in the received image, detecting a position of a character image in the received image, performing character recognition on the detected character image, comparing the position of the detected writing with the position of the detected character image to associate the writing with a result of the character recognition, translating the result of the character recognition so as to be recognizable as a translation of the result of the character recognition associated with the writing, generating an image of the translation result associated with the writing, so as to be output in a format different from a format of an image of a translation result that is not associated with the writing, and outputting the image of the translation result associated with the writing.

Abstract: Semantically meaningful segments of an image of a document, such as tables of contents, page numbers, footnotes, and the like, are identified. These segments form a model of the document image, which may then be rendered differently for different client devices. The rendering may be based on a display parameter provided by a client device, such as a display resolution of the client device, or a requested display format.

Abstract: A data input system includes: an image reader reading, on a form basis, an original image of each form filled with characters; extracting original image data pieces by dividing, on a character basis, the original image data, and setting identification information to each original image data piece for defining positions; for each original image data pieces, associated character-associated information; and making output with a correlation among the original image data pieces, the identification information set to each original image data piece, and the character-associated information for each original image data piece; and a data input receiver displaying any original image data piece selected according to a predetermined procedure; receiving input of text data to identify which character is represented by each original image data piece; and making storage by correlating the text data with the original image data pieces and the identification information set to each original image data piece.

Abstract: A method for inputting characters pairs in an electronic device having a user input device, a display for displaying characters input through the user input device, and a memory for storing characters input through the user input device, including storing a character input through the user input device in the memory and displaying the input character on the display; and determining if the input character is an opening character of a predefined character pair, and if so, automatically and without further user input, causing a corresponding closing character of the predefined character pair to be inserted in the memory and on the display, and locating an input pointer so that subsequently input characters will be inserted between the opening and closing characters in the memory and on the display.

Abstract: The claimed subject matter provides a system and/or a method that facilitates displaying relevant advertisements to a user. A display engine can browse a portion of image data during a browsing session. An evaluator can identify a context related to two or more concurrent and on-going browsing sessions. An ad selector can locate an ad from a data store based on the identified context and seamlessly incorporate and display the ad into at least one of the browsing sessions.

Abstract: A two-dimensional representation of a document is leveraged to extract a hierarchical structure that facilitates recognition of the document. The visual structure is grammatically parsed utilizing two-dimensional adaptations of statistical parsing algorithms. This allows recognition of layout structures (e.g., columns, authors, titles, footnotes, etc.) and the like such that structural components of the document can be accurately interpreted. Additional techniques can also be employed to facilitate document layout recognition. For example, grammatical parsing techniques that utilize machine learning, parse scoring based on image representations, boosting techniques, and/or “fast features” and the like can be employed to facilitate in document recognition.

Abstract: A method for optical character recognition (OCR) verification, the method includes: receiving a first character image that was obtained from applying an OCR process on a document; wherein the first character image is classified, by the OCR, as being associated with a first character; receiving a first character code of a text; replacing the first character code by the first character image; and evaluating a correctness of the OCR based upon a response of a user to a display of the text first character image.

Abstract: There is provided a character string updated degree evaluation program that enables quantitative grasping of an amount of intellectual work through editing and updating of character strings. A text subjected to comparison is divided into common part character strings each having a length greater than or equal to a threshold value, and non-common part character strings. A number of edited points from the original text and a context edit distance are calculated based on the rate of the common part character strings and the occurrence pattern thereof. A number of edited point is acquired from a number of elements contained in a common part character string set, and a context edit distance is acquired from a change in an order of occurrence of the common part character strings. Calculation of a new creation percentage and analysis by an N-gram are performed on the non-common part character string.

Abstract: A method for handwriting input includes recognizing a first character inputted by handwriting; providing a plurality of recognition results each with a code based on the recognition of the first character; recognizing a second character inputted by handwriting; and determining the first character based on the recognition of the second character. A handwriting input system for carrying out the method is also provided.

Abstract: Existing video surveillance security approaches enhanced with suitable functionality of the telecommunications wireless network are provided. Security personnel are equipped with hand-held devices capable of recording video, photos, audio, and text. This data is geo-tagged and time-stamped by the application and uploaded to the telecommunications network and stored in the network. As such, the geo-tagged, time-stamped information is immediately available to other investigators who are in the same geographic vicinity through access controls administered by a secure social network. The information may also be accessible from remote locations via the internet. All wireless and Internet communications may be protected using end-to-end secure transport layer communications protocols.

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: Provided herein are systems and method for obtaining contextual information of an image published on a digital medium. The methods and systems disclosed herein generally identify and analyze the image to obtain image descriptors corresponding to the image. The methods also identify and analyze text published proximate to the image to obtain textual descriptors, which function to describe, identify, index, or name the image or content within the image. The textual descriptors are then matched to the image descriptors to provide contextual information of the published image.

Abstract: Camera-based services are provided to a user of a portable communication device by recognizing text contained in an image. An image of an environment is captured using a camera within the portable communication device so as to obtain image data. The image data is processed such that text data is recognized and extracted from the image data. Data related to the text data is then output in a form recognizable by a user of the portable communication device. The text data can be processed on the portable communication device to obtain the data related to the text data. Alternatively, the processing is performed by a processing unit external to the portable communication device. Translated and audio versions of the text data are output to the user. One camera-based service provides price and product information related to a product described in an image captured by the camera.

Abstract: When a list of file names is to be displayed on a display device, a comparison is made between a necessary display width of each of the file names and a width of a display area of the display device. For each of the file names having a necessary display width greater than the width of the display area, it is checked whether the file name contains a particular character string portion of a predetermined type, and, if so, the file name is displayed in the list in a partly-omitted display style where a leading end portion, particular character string portion and extension of the file name are left in the list with the other part of the character string omitted. The particular character string portion can function as an important element for identifying the data item in question.

Abstract: There are provided a word search apparatus, a word search method, and a computer program product. A words dictionary, and a character recognition dictionary for storing coordinate data of a standard character pattern of a handwritten character and a character are used to thereby search for, from the words dictionary, a word including a character corresponding to one or a plurality of character patterns extracted by performing a pattern matching. Only a character string corresponding to one or a plurality of character patterns is extracted from a search result of the words dictionary to generate a part of character string. A selection of one part of character string among the generated parts of character strings is received, and only a word including the selected part of character string is extracted from the search result based on the words dictionary, so that the extracted word is displayed.

Abstract: The present invention relates to systems and methods for identifying captions associated with images in media material. A captioner includes a selector module and a caption identifier module. The selector module identifies text-blocks potentially associated with images in the media material. The caption identifier module identifies which text-blocks are captions associated with images in the media material, based on the textual and proximity features of the text-block and the images. The captioner may also include a caption feedback module to modify the determining of the caption identifier module.

Abstract: A method and system for recognizing text in computer images comprising distorted text provides an adaptive iterative process wherein recognition rules are adapted, added or omitted based on the present state of the recognition process. When the first pass through the recognition and adaptation is completed, the remaining unrecognized words (15) are passed through the recognition system 1 using the modified set of recognition rules stored in (18) and the process is repeated. In most cases the recognition system 1 will identify further reliable recognized words, which iteratively can be used to improve the recognition rules until the true text comprised in image (10) is recognized throughout the whole text. The steps of the method according to the present invention are thus repeated until convergence.

Abstract: A system and method, which enables precise identification of characters contained in vehicle license plates, container LD, chassis I.D, aircraft serial number and other such identification markings. The system can process these identified characters and operate devices, such as access control (126) operations, traffic systems and vehicle (20) and container tracking and management (170) systems, and provide records of all markings together with their images.

Abstract: A method and system are disclosed for matching input character sequences in a set of input patterns. The method comprises the steps of analyzing the set of input patterns, creating a pattern cluster look-up table (PCLT) based on said input patterns, and defining an offset value k. The PCLT is used to find, for each sequence s and offset k, a set of candidate patterns that can possibly match s, the set of candidate patterns is searched for patterns that match s, and all found matching patterns and sequences are reported.

Abstract: A technique that can contribute to a reduction in an operation burden in managing a processing result of semantic determination processing applied to objects included in an image is provided. An object included in an image of image data is extracted. A semantic of the object in a layout of the image data is determined. When it is determined that plural objects have an identical semantic, a display unit is caused to notify information concerning the plural objects, which are determined as having the semantic, in association with information concerning the semantic.

Abstract: Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.

Abstract: An apparatus for masking text in a rendered copy of an original document includes a text modification system which is configured to receive a print job from an application and modify the print job in accordance with a print job description, whereby when rendered on an output device, a selected text element is masked. A user interface is configured to receive instructions from a user to build the print job description including instructions for selecting text elements to be masked.

Abstract: In embodiments of the present invention improved capabilities are described for scanning a data set for the presence of a target string. The data set may be received at a computing facility and cause a scanning program to execute. A first character pair in the data set may be identified where each character making up the first character pair is identified in a vector map. It may then be confirmed that the first character pair matches a positive indicated bitmask in a bitmap matrix, and verify that the position of the first character pair matches a position of a matching character pair in the target string. An action may be caused to be taken as a result of the verification.

Abstract: Systems and methods for character-by-character alignment of two character sequences (such as OCR output from a scanned document and an electronic version of the same document) using a Hidden Markov Model (HMM) in a hierarchical fashion are disclosed. The method may include aligning two character sequences utilizing multiple hierarchical levels. For each hierarchical level above a final hierarchical level, the aligning may include parsing character subsequences from the two character sequences, performing an alignment of the character subsequences, and designating aligned character subsequences as the anchors, the parsing and performing the alignment being between the anchors generated from an immediately previous hierarchical level if the current hierarchical level is below the first hierarchical level. For the final hierarchical level, the aligning includes performing a character-by-character alignment of characters between anchors generated from the immediately previous hierarchical level.

Abstract: An image of a character string composed of M pieces of characters is clipped from a document image, and the image is divided character by character, and image features of each character image are extracted. On the basis of the image features, N (N>1, integer) pieces of character images in descending order of degree of similarity are selected as candidate characters from a character image feature dictionary which stores the image features of character image in units of character, and the first index matrix of M×N cells is prepared. A candidate character string composed of a plurality of candidate characters constituting the first column of the first index matrix, is subjected to a lexical analysis according to a predetermined language model, whereby a second index matrix adjusted into a character string which makes sense is prepared to be utilized for searching.

Abstract: Restriction information on a total colorant amount for a medium is obtained. Patches at grid points in a color space corresponding to a plurality of colorants at which the total colorant amount falls within a restriction represented by the restriction information, and a patch at a point surrounded by the patches are generated. Color values are obtained by measuring the colors of the patches printed on the medium. It is determined based on a color prediction value between the grid points whether the measured color values are appropriate, and if so, a color value at a grid point at which the total colorant amount exceeds the restriction is estimated based on the measured color values. A color separation table is created based on the measured color values and the estimated value.

Abstract: A facility for storing a text capture data structure for a particular user is described. The data structure comprises a number of entries. Each entry corresponds to a text capture operation performed by the user from a rendered document. Each entry contains information specifying the text captured in the text capture operation.

Abstract: The invention relates to the authentication of users for a multi-function peripheral (MFP) device using handwritten signatures. Systems and methods are disclosed which relate to a MFP that conditions access to MFP operations based on an authenticating process that compares a prospective user's signature to previously saved signatures. The signatures are communicated to the MFP using the MFP's native scanning function.

Abstract: A method of controlling a display of an electronic device for displaying a list of electronic messages. The method includes comparing a width of a designated space for a field of the electronic messages to a minimum width to determine if the width is sufficient, and if the width is determined to be sufficient, maintaining the width of the designated space, otherwise increasing the width of the designated space.

Abstract: According to one embodiment, a character recognition apparatus includes a detection unit and a recognition unit. The detection unit detects each character candidate from an image. The recognition unit recognizes each character candidate based on a plurality of character recognition dictionaries corresponding to a plurality of degrees of different character chipping.

Abstract: The color printing control device outputs color material reduction processed data generated by applying a color material reduction process to each pixel of bitmaps converted to color material colors to be used in printing, when it is judged that the color material reduction printing mode is specified. The color material reduction process includes chroma conversion that reduces chroma and under-color removal/black generation that replaces at least a portion of achromatic components generated by overlaying of a plurality of color materials.

Abstract: There is provided an image processing apparatus including a character recognition section that executes character recognition on an input document image and outputs a character recognition result, an item name extraction section that extracts a character string relevant to an item name of an information item from the character recognition result, an item value extraction section that extracts a character string of an item value corresponding to the item name from the vicinity of the character string relevant to the item name in the document image, and an extraction information creation section that creates extraction information by associating the character string of the item value extracted by the item value extraction section to the item name.

Abstract: In one embodiment, a method of tagging content can include: accessing a frame of a digital media production; identifying an object for tagging within the frame; defining a metadata tag for the object; and storing the metadata tag in association with the identified object and the frame in the digital media production. In one embodiment, a method of substituting content can include: receiving tagged digital media in a controller; identifying an object for substitution by searching through objects and metadata tags in the tagged digital media; retrieving a substitute object using the controller; and re-rendering the tagged digital media to produce a customized digital media using the substitute object in place of the identified object.

Abstract: Words possibly included in a scene image shot by a mobile camera can be efficiently extracted using a word dictionary or a map database. Positional information acquiring means 101 measures a current position of the device to acquire positional information. Directional information acquiring means 102 detects a direction of the device to acquire directional information. Character recognizing means 104 determines a range of shooting of a scene image based on the current positional information and the directional information. The character recognizing means 104 extracts from a map database 103 information such as store names, building names, and place names associated with positions in the shooting range. Then the character recognizing means 104 conducts character recognition using word knowledge such as the extracted store names, building names, and place names.