Abstract: An information processing apparatus includes a reading unit, a recognition unit, a table-of-contents analysis unit, a main-body analysis unit, and a creation unit. The reading unit reads a table of contents page and a main body page as images. The recognition unit performs character recognition on the images of the table of contents and main body pages. The table-of-contents analysis unit analyzes the image of the table of contents page, and acquires at least a heading item in accordance with a result of character recognition. The main-body analysis unit analyzes the image of the main body page, and associates an image including the heading item with the heading item in accordance with a result of character recognition. The creation unit creates electronic bookmarked information in which bookmark information for associating the heading item with the image of the main body page is added to electronic information of the read images.

Abstract: Methods and systems for segmenting printed media pages into individual articles quickly and efficiently. A printed media based image that may include a variety of columns, headlines, images, and text is input into the system which comprises a block segmenter and an article segmenter system. The block segmenter identifies and produces blocks of textual content from a printed media image while the article segmenter system determines which blocks of textual content belong to one or more articles in the printed media image based on a classifier algorithm. A method for segmenting printed media pages into individual articles is also presented.

Abstract: An automated method for identifying images in an image database based on scores assigned to a plurality of input keywords. Each input keyword is assigned a keyword score based on the number of images in the database that are associated with that keyword. Each image in the database is then assigned an image similarity score based on the keyword scores of the input keywords associated with that image. If a user selects an image in the image database and requests to see similar images, the keywords associated with the selected image are used as input keywords. Images in the database with image similarity scores indicating greatest similarity are provided to the user.

Abstract: Data validation techniques are provided. For example, such techniques complement user entries associated with events of interest through context. In one aspect of the invention, a technique for processing one or more user entries associated with one or more events of interest includes the following steps/operations. Context associated with the one or more events of interest is obtained. At least a portion of the obtained context is associated with one or more user entries representing events of interest. At least a portion of the one or more user entries is evaluated, responsive to at least a portion of the context. An indication of the one or more events of interest is provided, responsive to the evaluation.

Abstract: An information processing system assigns a comment to a specific region of an image, and calculates a total value of evaluation scores based on assigned comments for each image as an evaluation value of that image.

Abstract: A packet is compared to a pattern defined by a regular expression with back-references (backref-regex) in a single pass of a non-deterministic finite automaton corresponding to the backref-regex (backref-NFA) that includes representations for all backref-regex's back-references. The packet's characters are sequentially selected and analyzed against the backref-NFA until a match or no-match between the packet and pattern is determined. Upon selecting a character, a corresponding configurations-set is updated, where the set includes configurations associated with respective NFA-states of the backref-NFA and indicating whether the selected character is being matched against a back-reference. With the configurations-set being updated the comparison process proceeds along backref-NFA's NFA-states. The updated configurations-set includes configurations associated with NFA-states reachable from the configurations in the pre-updated set. When the configurations-set includes a final state, a match is determined.

Abstract: An information processing apparatus includes, a first database in which an imaging device is previously associated with an owner of the imaging device among a plurality of persons, a second database in which the persons are previously associated with their respective personal images, a first determining unit to acquire information about the imaging device associated with an image of interest to be served as an object to be estimated as a photographer, a second determining unit to acquire a second value that represents a probability that each of persons is a photographer of the image of interest, based on a result of making a comparison between a subject image included in the image of interest and each personal image in the second database, and a third determining unit to acquire a third value that represents a probability that each of persons is a photographer of the image of interest.

Abstract: Systems and methods are described that facilitate identifying objects in a document (e.g., a PDF document) for automatic image enhancement (AIE). A PDF document is “chunked” or segmented into chunks, and boundaries between chunks are identified as real or imaginary. Chunks sharing imaginary boundaries are combined, while real boundaries are retained, to generate “de-chunked” objects. These objects are then classified, and an AIE application is executed on objects meeting pre-specified classification criteria. In this manner, objects of r which AIE is not desired are not subjected to the AIE application, thereby saving time and processing resources associated with enhancing the document.

Abstract: Techniques and structures are disclosed in which one or more distortion categories are identified for an image or video, and a quality of the image or video is determined based on the one or more distortion categories. The image or video may be of a natural scene, and may be of unknown provenance. Identifying a distortion category and/or determining a quality may be performed without any corresponding reference (e.g., undistorted) image or video. Identifying a distortion category may be performed using a distortion classifier. Quality may be determined with respect to a plurality of human opinion scores that correspond to a particular distortion category to which an image or video of unknown provenance is identified as belonging. Various statistical methods may be used in performing said identifying and said determining, including use of generalized Gaussian distribution density models and natural scene statistics.

Abstract: A storage medium storing an image processing program in which the image processing program obtains a plurality of images and displacement information indicating a positional displacement between the plurality of images, calculates weighting information for performing weighting processing on the displacement information for each of a plurality of color components, performs the weighting processing on the displacement information for each of the plurality of color components, calculates a pixel value of a color component of a calculation target based on local inflection information of a color component other than the color component of the calculation target and the weighting information after conducting the weighting processing, and generates a composite image based on a calculation result. Accordingly, it is possible to reduce a processing time in image processing which generates, from the plurality of images having the positional displacement, the composite image having a higher resolution than those images.

Abstract: A computer-implemented method of managing information is disclosed. The method can include receiving a message from a mobile device configured to connect to a mobile device network (the message including a digital image taken by the mobile device and including information corresponding to words), determining the words from the digital image information using optical character recognition, indexing the digital image based on the words, and storing the digital image for later retrieval of the digital image based on one or more received search terms.

Abstract: A character string extraction device according to the present invention includes a replacement information registering unit in which replacement information to replace character information expected to be erroneously recognized is registered, a candidate character data registering unit in which supposed candidate character data is registered, an image information converting unit for converting the read image information into character information, a character information replacing unit for replacing a specific character with a designated character when the character information includes the specific character and generating read character data by using the converted character information when the character information does not include the specific character, a search character generating unit for replacing a predetermined character of the read character data with a special character and, generating search character data from the read character data, and a first comparing unit for comparing the search characte

Abstract: Embodiments include a scene classification system and method. In one embodiment, a method includes forming a first plurality of image features from an input image, processing the first plurality of image features in the first scene classifier.

Abstract: Systems, apparatuses, and methods to relate images of words to a list of words are provided. A trellis based word decoder analyses a set of OCR characters and probabilities using a forward pass across a forward trellis and a reverse pass across a reverse trellis. Multiple paths may result, however, the most likely path from the trellises has the highest probability with valid links. A valid link is determined from the trellis by some dictionary word traversing the link. The most likely path is compared with a list of words to find the word closest to the most.

Abstract: A data verification system is configured to verify machine-recognized data elements acquired during a machine-implemented data acquisition process. The system includes a data verification workstation, an image server, and a data entry server. The data verification workstation is configured to obtain document images from the image server, present portions of document images to an operator, wherein the document images include text, and receive input from the operator based on the text. The input includes data elements. The data verification workstation is also configured to acquire machine-recognized data elements from the data entry server. The machine-recognized data elements were acquired from the document image during a machine-implemented data acquisition process based on the text.

Abstract: An image forming apparatus includes a receiving unit that receives image data; an extracting unit that extracts specific information from the image data; a first recognizing unit that recognizes destination information from the specific information; and a control unit that outputs the image data, wherein, when the first recognition unit recognizes a plurality of destination information, the control unit outputs the image data to respective destinations corresponding to each of the plurality of the destination information.

Abstract: Image processing apparatus and method perform a character recognition process to an area indicating a character string included in image data, generate layout information for layout of the character string on the basis of the area, and perform layout of a result of the character recognition process on the basis of the generated layout information, thereby enabling to perform a process, which uses the layout information, to a document which includes various layouts.

Abstract: An object recognition and event representation system includes: a server and a broadcaster, coupled to the server. In response to a request from the broadcaster, the server sends an event metadata and a recognition data. Based on the event metadata and the recognition data, the broadcaster simultaneously performs a live video broadcasting and a real-time object recognition. If the broadcaster recognizes an object, the broadcaster sends a recognition result to the server.

Abstract: An information processing apparatus includes a face detecting unit configured to detect a face in an image; a discriminating unit configured to discriminate an attribute of the face detected by the face detecting unit; a generating unit configured to generate, from the face detected by the face detecting unit and the attribute discriminated by the discriminating unit, a feature amount of the image; and a learning unit configured to learn, from the feature amount generated by the generating unit, information for discriminating whether the image corresponds to a predetermined scene.

Abstract: Systems and methods for automatically extracting parallel word sequences from comparable corpora are described. Electronic documents, such as web pages belonging to a collaborative online encyclopedia, are analyzed to locate parallel word sequences between electronic documents written in different languages. These parallel word sequences are then used to train a machine translation system that can translate text from one language to another.

Abstract: A method of aided input especially for a computer management tool, the management tool being executed in a computer system possessing an operating system furnished with instrumentation services, the method including the following steps: (a) entering raw data from an exterior source, (b) extracting relevant data from the raw data, (c) using the instrumentation services to transcribe the extracted data to corresponding fields of a preexisting input interface belonging to the management tool, within a view to allowing further inputs and overall validation. Application in particular to the semi-automated input of accounting items such as supplier invoices and the like.

Abstract: A mobile terminal including a wireless communication unit configured to wirelessly communicate with at least one other terminal; a display configured to display a first screen layer corresponding to one of a back screen of the mobile terminal and an execution screen of an application installed on the mobile terminal, and to display a second screen layer corresponding to a note function of the mobile terminal; and a controller configured to control the display to selectively display the second screen layer based on an input request for requesting the second screen layer, to receive a touch input on the first or second screen layers and to execute a function corresponding to the received touch input on the first or second screen layers.

Abstract: An input signal is converted to a feature-space representation. The feature-space representation is projected onto a discriminant subspace using a linear discriminant analysis transform to enhance the separation of feature clusters. Dynamic programming is used to find global changes to derive optimal cluster boundaries. The cluster boundaries are used to identify the segments of the audio signal.

Abstract: A live video stream captured by an on-device camera is displayed on a screen with an overlaid guideline. Video frames of the live video stream are analyzed for a video frame with acceptable quality. A text region is identified in the video frame approximate to the on-screen guideline and cropped from the video frame. The cropped image is transmitted to an optical character recognition (OCR) engine, which processes the cropped image and generates text in an editable symbolic form (the OCR'ed text). A confidence score is determined for the OCR'ed text and compared with a threshold value. If the confidence score exceeds the threshold value, the OCR'ed text is outputted.

Abstract: Provided herein is a method and apparatus for more effectively and accurately inputting a character string through a gesture input, and the apparatus for inputting a character string associated with an embodiment of the present invention may include a keypad for inputting a gesture generated by touch motion; a memory configured to store at least one of a gesture, character string information corresponding to the gesture, and a gesture input from the keypad; a controller configured to identify a character string corresponding to the gesture input from the keypad to extract a character string corresponding to the identified character string or including the identified character string among the character strings previously stored in the memory; and a display unit configured to display the extracted character string under a control of the controller.

Abstract: An information processing apparatus of the present invention selects one language group, then selects one language from the selected language group, and performs OCR processing appropriate for the selected language on characters included in an image. From an obtained OCR processing result, a matching degree indicating a degree of similarity between the recognized characters in the image and the language selected for the OCR processing is calculated. Then, in a case where the matching degree is equal to or smaller than a particular value, a language belonging to a different language group is selected to further perform OCR processing. The efficiency of the OCR processing is improved. The information processing apparatus of the present invention allows improvement in the efficiency of the OCR processing.

Abstract: A wordspotting system and method are disclosed. The method includes receiving a keyword and, for each of a set of typographical fonts, synthesizing a word image based on the keyword. A keyword model is trained based on the synthesized word images and the respective weights for each of the set of typographical fonts. Using the trained keyword model, handwritten word images of a collection of handwritten word images which match the keyword are identified. The weights allow a large set of fonts to be considered, with the weights indicating the relative relevance of each font for modeling a set of handwritten word images.

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: A scanning capability for capacitive touch screen devices is disclosed. Images, such as text, barcodes, or the like are printed on printed objects, such as business cards, information cards, and the like using electrically conductive ink that has had electrical properties imparted thereon such that, when the printed object comes in contact with the touch screen of a capacitive touch screen device, the imparted electrical properties are sufficient to cause variances in capacitance to the touch screen that are detectable by the device. Using these detected touches, the scanning system analyzes any patterns created by the detected touches to determine information represented by those patterns and corresponding to the information represented by the images printed on the printed object.

Abstract: Techniques for capturing images of business cards, uploading the images to a designated computing device for processing and recognition are disclosed. A mechanism is provided to update extracted data from the images when there are any changes. Depending on implementation, there are a number of ways to capture images of business cards (e.g., via a phone camera, a PC camera, or a scanning device). A transmission means is provided to transport the images to the designated computing device for centralized management of integrated contact information for individual users. As a result, a user may access his/her updatable integrated contact information database anywhere anytime from a chosen device.

Abstract: Word correlations are estimated using a content-based method, which uses visual features of image representations of the words. The image representations of the subject words may be generated by retrieving images from data sources (such as the Internet) using image search with the subject words as query words. One aspect of the techniques is based on calculating the visual distance or visual similarity between the sets of retrieved images corresponding to each query word. The other is based on calculating the visual consistence among the set of the retrieved images corresponding to a conjunctive query word. The combination of the content-based method and a text-based method may produce even better result.

Abstract: Methods and systems for fast, large scale, high-dimensional searches are described. In some embodiments, a method comprises transforming components of a high-dimensional image descriptor into transformed components in a transform domain, allocating one or more bits available within a bit budget to a given transformed component within a first subset of transformed components as a function of a variance of the given transformed component, independently quantizing each transformed component within the first subset of transformed components, generating a compact representation of the high-dimensional image descriptor based, at least in part, on the independently quantized components, and evaluating a nearest neighbor search operation based, at least in part, on the compact representation of the high-dimensional image descriptor.

Abstract: A system for processing a text capture operation is described. The system receives text captured from a rendered document in the text capture operation. The system also receives supplemental information distinct from the captured text. The system determines an action to perform in response to the text capture operation based upon both the captured text and the supplemental information.

Abstract: An image processing apparatus and control method capable of providing character information are disclosed the apparatus includes a signal receiving unit which receives an image signal; an image processing unit which processes the received image signal so that an image based on the image signal can be displayed; a searching unit which searches search words; and a controller which controls the searching unit to search at least one of the search words included in the displayed image and provide a user with a result of the search for the search word. With this configuration, users can more conveniently search character information included in contents being watched.

Abstract: Methods, systems, and apparatus, including computer program products, for generating data for annotating images automatically. In one aspect, a method includes receiving an input image, identifying one or more nearest neighbor images of the input image from among a collection of images, in which each of the one or more nearest neighbor images is associated with a respective one or more image labels, assigning a plurality of image labels to the input image, in which the plurality of image labels are selected from the image labels associated with the one or more nearest neighbor images, and storing in a data repository the input image having the assigned plurality of image labels. In another aspect, a method includes assigning a single image label to the input image, in which the single image label is selected from labels associated with multiple ranked nearest neighbor images.

Abstract: Cellular telephone camera used to obtain an image, and to produce an output that helps recognize the words within that image, for example, a menu or a bill in a restaurant. The cellular telephone can have a low-light camera device so that it can obtain images in low light. The image processing can recognize characters in the image and display those characters using the phone's own internal font(s).

Abstract: A method and device is provided for recognizing characters in a handwritten input representing an input character string. A character sub-string preceding an unrecognized character in the input character string is determined. Handwriting recognition is used to provide one or more candidate characters for the unrecognized character. One of the one or more candidate characters is then selected. The candidate character selected, is the one which is most likely to be a correct recognition of the unrecognized character based on the determined character sub-string.

Abstract: A character line recognition method for processing image data obtained by scanning a character line on a medium to recognize the character line may include processing the image data into monochrome binary format image data by using a predetermined binarization standard threshold; extracting character features from each character that composes the character line to calculate similarity with respect to standard character features; temporarily determining characters based on the similarity; calculating basic statistics of the similarity for all the characters which have been temporarily determined; and changing the binarization standard threshold based on the basic statistics and then returning to the processing the image data.

Abstract: A data verification system is configured to verify machine-recognized data elements acquired during a machine-implemented data acquisition process. The system includes a data verification workstation, a image server, and a data entry server. The data verification workstation is configured to obtain document images from the image server, present portions of document images to an operator, wherein the document images include text, and receive input from the operator based on the text. The input includes data elements. The data verification workstation is also configured to acquire machine-recognized data elements from the data entry server. The machine-recognized data elements were acquired from the document image during a machine-implemented data acquisition process based on the text.

Abstract: A method for identifying words in a textual image undergoing optical character recognition includes receiving a bitmap of an input image which includes textual lines that have been segmented by a plurality of chop lines. The chop lines are each associated with a confidence level reflecting a degree to which the respective chop line properly segments the textual line into individual characters. One or more words are identified in one of the textual lines based at least in part on the textual lines and a first subset of the plurality of chop lines which have a chop line confidence level above a first threshold value. If the first word is not associated with a sufficiently high word confidence level, at least a second word in the textual line is identified based at least in part on a second subset of the plurality of chop lines which have a confidence level above a second threshold value lower than the first threshold value.

Abstract: A system and method for character error correction is provided, useful for a user of mobile appliances to produce written text with reduced errors. The system includes an interface, a word prediction engine, a statistical engine, an editing distance calculator, and a selector. A string of characters, known as the inputted word, may be entered into the mobile device via the interface. The word prediction engine may generate word candidates similar to the inputted word using fuzzy logic and user preferences generated from past user behavior. The statistical engine may generate variable error costs determined by the probability of erroneously inputting any given character. The editing distance calculator may determine the editing distance between the inputted word and each of the word candidates by grid comparison using the variable error costs. The selector may choose one or more preferred candidates from the word candidates using the editing distances.

Abstract: A method for producing a slide show video from a collection of hardcopy media, the method includes digitizing the media and detecting handwritten information and estimating the age of the media; determining an order of presentation for the slide show video based on the detected handwritten information and estimated ages; and producing a slide show video from the hardcopy media using the determined order of presentation.

Abstract: A system and method is provided wherein, in one aspect, a number of different elements are presented to a user. The user is instructed to pick the elements that are the most related to one another. If the user selects the two most related elements, the user is presented with access to additional information, such as a screen for creating an email account. The system and method are intended to allow access to information by humans, but not remote computers emulating a human.

Abstract: A method of recognizing an event depicted in an image from the image and a location information associated with the image is disclosed. The method includes acquiring the image and its associated location information; using the location information to acquire an aerial image(s) correlated to the location information; identifying the event using both the image and the acquired aerial image(s); and storing the event in association with the image for subsequent use.

Abstract: An image processing apparatus includes a receiving unit that receives a size of a first character sequence component, a direction from a prefix character sequence component as a character sequence component, which is prefixed before the first character sequence component, to the first character sequence component, and a distance from the prefix character sequence component to the first character sequence component, a predicting unit that predicts a second character sequence component following the first character sequence component, a detecting unit that detects the second character sequence component in the image, a correcting unit that corrects information relating to the second character sequence component detected by the detecting unit, and a control unit that controls the receiving unit to receive as a next first character sequence component the corrected second character sequence component and causes the predicting unit, the detecting unit, and the correcting unit to repeat processing.

Abstract: An image processing apparatus includes: a character recognition section for performing a character recognition process and a formatting process section for generating an image file in which text data obtained by the character recognition process are associated with the image data, the character recognition section generating the text data corresponding respectively to a plurality of possible character recognition results. This makes it possible to prevent omission in search in a case where a keyword search based on the text data is carried out, in the image processing apparatus that generates an image file in which image data obtained by reading a document is associated with text data obtained by a character recognition process on the image data.

Abstract: Techniques for capturing images of business cards, uploading the images to a designated computing device for processing and recognition are disclosed. A mechanism is provided to update extracted data from the images when there are any changes. Depending on implementation, there are a number of ways to capture images of business cards (e.g., via a phone camera, a PC camera, or a scanning device). A transmission means is provided to transport the images to the designated computing device for centralized management of integrated contact information for individual users. As a result, a user may access his/her updatable integrated contact information database anywhere anytime from a chosen device.

Abstract: Systems and methods are provided for capturing and processing images of remittance coupons using a mobile device and obtaining data from the captured image which is used to set up or carry out payment of a bill that corresponds to the remittance coupon. Optimization and enhancement of image capture and image processing are provided on the mobile device to improve the initial quality of the captured image and provide a user with real time feedback. The image is then sent from the mobile device to a remote server, where additional image processing is performed to improve the quality of the image and then extract data from the image that is relevant to paying the bill. The extracted data may be verified through comparisons with databases which store information on billers, bill formats and other relevant content that will appear on the bill.

Abstract: A system for interactive paper is described. Data fragments are captured at locations in a rendered document. A digital version of the document is optionally located. Markup data applied to the capture creates a rich set of interactions for the user. New models for publishing documents and new document-related services are described.

Abstract: An apparatus, method, and system for processing character data is provided, which selects a format of the character data to be used for generating print data. When a user instruction for printing character data according to character command data specifying the output of the character data is received, the format of the character data is selected based on the character command data.