Abstract: A machine-learning system analyzes electronic books to determine a “start-of-reading location” (SRL) in each book. Based on this location, when an electronic book is opened on a reading device for the first time, the book can be opened to where a reader is likely to want to start reading, automatically skipping past introductory pages. Books are divided into logical blocks (e.g., title page, forward, chapters, etc.), and a title portion and a body-text portion is identified in each block. A title classifier attempts to determine whether or not a block should be marked as the SRL. If the score from the title classifier is indefinite, a body-text classifier is used.

Abstract: A terminal device includes a processor that executes a process including extracting multiple character strings, in units of rows, from a character area included in an image data, and enlarging and displaying one of the extracted plurality of character strings in a designated position of a designated row and the vicinity of the designated position.

Abstract: Embodiments of the present invention provide methods and apparatuses for coding and decoding a depth map. The coding method includes: obtaining prediction data corresponding to a current image block of the depth map, obtaining a predicted pixel value from the prediction data according to a preset step, and calculating a first average value of the prediction data according to the predicted pixel value, where the preset step is a positive integer except 1; obtaining a residual of the current image block according to the first average value of the prediction data and a pixel value of a pixel of the current image block; and coding the residual of the current image block. In this way, coding and decoding efficiency can be improved.

Abstract: A method and a device for adjusting and displaying an image are provided. The method includes: monitoring the distance between a user in front of a display screen and the display screen; when monitoring that a distance between the user and the display screen is less than a preset threshold, determining an adjusted size of an image on the display screen according to the distance; and displaying the image on the display screen according to the adjusted size.

Abstract: To better realize the great potential of amateur digital photography, the present invention introduces an integrated system for the acquisition, organization, manipulation, and publication of digital images by amateur digital photography enthusiasts. The system of the present invention first acquires images from a number of different image sources. Images acquired in the same image importing session are marked as coming from the same conceptual film roll. Next, a user is empowered to organize and manipulate the acquired images. The images may be organized by tagging the images with informative keywords and grouping images together into conceptual photo albums. Furthermore, the images may be manipulated by rotating, cropping, and removing red-eye. Finally, the system of the present invention provides simple intuitive image publish systems.

Abstract: A computer-implemented method for detecting a presence of an object-of-interest in a system is provided. The method includes imaging the first object-of-interest including an identifier, wherein the imaging generates a first set of image data and determining the portion of the image data including the identifier based on a predetermined location. The method further includes dividing the portion of the image data including the identifier into at least two segments Next, the presence of the object-of-interest is determined by determining if intensity values within each segment exceed a presence threshold.

Abstract: Image filter values can be obtained by applying a high-frequency or edge-detection image filter to an image to extract a level of image detail. The image can be divided into blocks of a predetermined size and the image filter values of the pixels in a block can be used to obtain a density value associated with the level of image detail for the block. For blocks where the density value exceeds a threshold amount, a degree of blur may be applied based on the density value. Thus, the image can be rendered so that only some of the blocks of the image are blurred while other blocks do not have blur applied.

Abstract: A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.

Abstract: Methods, systems and articles of manufacture for generating interface elements of an electronic tax preparation application to allow a taxpayer or user to view a portion of an image of a tax document that is a source of data for a field of a screen generated by the electronic tax application. The image portion displayed may be a particular box or field of a tax document for a corresponding particular field of the screen generated by the electronic tax preparation or a bounding region including one or more adjacent or surrounding boxes or fields. Embodiments allow taxpayers to view an image of a source document while viewing the data that was entered in the field from within the tax preparation application without having to consult paper copies of the tax documents.

Abstract: Provided is an information processing device including a data processing unit that executes reproduction processing of content recorded in an information recording medium. The content includes an individual segment region formed of a plurality of variation data in which identification information different from each other is embedded and each of which can be decrypted by a different key, and a common segment region formed of single data. The variation data is formed of a 6144 byte aligned unit. The data processing unit calculates a reproduction path by applying a device key held in a memory, and selects an aligned unit corresponding to one variation data that corresponds to the calculated reproduction path from a plurality of aligned units configuring the plurality of variation data in the individual segment region included in the data read from the information recording medium, and then, executes the decryption and reproduction processing.

Abstract: A method and corresponding apparatus relate to converting a nondeterministic finite automata (NFA) graph for a given set of patterns to a deterministic finite automata (DFA) graph having a number of states. Each of the DFA states is mapped to one or more states of the NFA graph. A hash value of the one or more states of the NFA graph mapped to each DFA state is computed. A DFA states table correlates each of the number of DFA states to the hash value of the one or more states of the NFA graph for the given pattern.

Abstract: A computer receives user preferences. The computer receives a document, wherein the document includes an image. The computer determines that the image contains embedded text. The computer determines that the embedded text does not satisfy the received user preferences. The computer modifies the embedded text to satisfy user preferences.

Abstract: A method of extracting text from a digital image is provided. The method of extracting text includes receiving a digital image at an image processor where the digital image includes a textual object and a graphical object. A mask is generated based on the digital image. The mask includes a pattern having a first pattern area associated with the textual object and a second pattern area associated with the graphical object. The mask is applied to the digital image creating a transformed digital image. The transformed digital image includes a portion of the digital image associated with the textual object. Character recognition is performed on the portion of the digital image associated with the textual object of the transformed digital image to create a recognized text output.

Abstract: An information processing apparatus includes a memory, an accepting unit, a determining unit, and a selecting unit. The memory stores a template collection. The memory associatively stores, for each template, the template and a degree of first impression similarity indicating an impression of the template. The accepting unit accepts an image. The determining unit determines an impression of the accepted image. The selecting unit selects, from the template collection, a template that is in harmony with the image by using a degree of second impression similarity indicating the impression of the image, and the degree of first impression similarity.

Abstract: For extracting data from a document with fixed structure, we recognize key words in an image of the document; identify reference object based on these key words, create templates based on the identified reference objects; match the created templates against the image of the document while recognizing fields in the image of the document these templates; and select the best template using quality of the recognized field.

Abstract: A method for image processing, including: obtaining an image including a table; identifying a first plurality of geometric lines in the image; grouping the first plurality of geometric lines into a plurality of clusters; determining a plurality of hand-drawn lines in the image corresponding to the table from the plurality of clusters; calculating a plurality of points for the plurality of hand-drawn lines; and determining a geometry of the table based on the plurality of points.

Abstract: A method for parsing the text of a complex graphical image comprises obtaining a series of blocks of text from a complex graphical image. Those blocks of text are used to generate location scores, size scores and length scores. Each of the scores is weighted and linearly summed. The highest resulting sum is identified as the most likely to be a desired text block.

Abstract: Apparatus for matching a query image against a catalog of images, comprises: a feature extraction unit operative for extracting principle features from said query image; a relationship unit operative for establishing relationships between a given principle feature and other features in the image, and adding said relationships as relationship information alongside said principle features; and a first comparison unit operative for comparing principle features and associated relationship information of said query image with principle features and associated relationship information of images of said catalog to find candidate matches.

Abstract: A reference image is generated by converting a vector image into a raster image, a temporarily-compressed image is generated by compressing the raster image according to a compression ratio, a comparison image of the same size as the reference image is generated by subjecting the temporarily-compressed image to interpolation enlargement processing, the above processing is repeated while varying the compression ratio if the error ratio between the reference image and the comparison image is greater than a benchmark error ratio, the above processing is repeated while varying the benchmark error ratio if the image volume of the temporarily-compressed image is greater than a predetermined memory capacity when the error ratio is at or under the benchmark error ratio, and the temporarily-compressed image is stored in memory as a compressed image of a vector image if the image volume of the temporarily-compressed image is at or under the memory capacity.

Abstract: A method of crawling a graphical user interface (GUI) based application may include performing a first-time crawl of a first sequence of actions of the GUI-based application. The first-time crawl may be a first time that the first sequence of actions is crawled. Further, the first sequence of actions may be a prefix of a second sequence of actions that includes one or more additional actions than the first sequence of actions. The method may also include extending the first-time crawl by the one or more additional actions such that the second sequence of actions is crawled during the first-time crawl. Further, the method may include determining a first input/output sequence associated with the first sequence of actions based on the first-time crawl. Additionally, the method may include determining a second input/output sequence associated with the second sequence of actions based on the first-time crawl.

Abstract: A computer method and system for providing information results in response to a natural language information request. The system and method include receiving a natural language information request from a user and compiling a computer executable query from the natural language information request from a user wherein the query is formatted to extract data from one or more computer databases. The query is then presented to the user prior to execution of the query so as to enable the user to change the query prior to its execution. The query is then executed to extract data from one or more computer databases whereby extracted data is presented to the user in a certain presentation format.

Abstract: A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.

Abstract: Provided is an image search system capable of searching for an image that differs in a specific part from an original image. A reception unit receives designation of a partial region in an original image to be processed and a process content for the partial region. A search unit searches for an image identical or similar to a processed image, which is obtained by applying a process of the process content to the partial region of the original image, based on: a plurality of kinds of feature information on a region other than the partial region of the processed image or of the original image; and at least one piece of feature information selected based on the process content from among a plurality of kinds of feature information on the partial region of the processed image or of the original image.

Abstract: A method to generate an effective schema of an electronic document for optimizing the processing thereof may include performing a programmatic analysis to determine all required portions of the electronic document. The method may also include generating a parser or deserializer to build an optimized document model; and specializing a document processing program against the optimized document model.

Abstract: Methods for optimizing a scale and position of a document in response to a user input is provided are provided. In one aspect, a method includes receiving an initial input request to scroll a document to a target position of the document, and identifying at least one relevant portion of content at or near the target position of the document. The method also includes adjusting a position and scale of the document while receiving the initial input request to an optimal position and an optimal scale for viewing the at least one relevant portion. Systems and machine-readable media are also provided.

Abstract: A method for classifying objects from one or more images comprising generating a trained classification process and using the trained classification process to classify objects in the images. Generating the trained classification process can include extracting features from one or more training images and clustering the features into one or more groups of features termed visual words; storing data for each of the visual words, including color and texture information, as descriptor vectors; and generating a vocabulary tree to store clusters of visual words with common characteristics. Using the trained classification process to classify objects can include extracting features from the images and clustering the features into groups of features termed visual words; searching the vocabulary tree to determine the closest matching clusters of visual words; and classifying objects based on the closest matching clusters of visual words in the vocabulary tree.

Abstract: A method performed by an electronic device is described. The method includes generating a plurality of bounding regions based on an image. The method also includes determining a subset of the plurality of bounding regions based on at least one criterion and a selected area in the image. The method further includes processing the image based on the subset of the plurality of bounding regions.

Abstract: A method and system generates an idealized image of a form. An image of a form and a template model of the form are received. The form includes data fields. Word boxes of the image are identified. The word boxes are assigned to corresponding data fields of the form. An idealized image of the from is generated based on the assignments and the template model.

Abstract: A method for detecting texts included in an image is disclosed. The method includes steps of: (a) detecting at least one text candidate in an inputted image by referring to feature values of pixels in the inputted image; (b) classifying (i) the detected text candidate as a strong text or a non-strong text by referring to a comparison result between a first threshold value and a first feature value and (ii) the text candidate classified as the non-strong text as a weak text or a non-text by referring to a comparison result between a second threshold value and a second feature value; and (c) determining whether to classify the weak text as the strong text by referring to information on the strong text and information on the weak text.

Abstract: Systems and methods for extracting text from images rendered on a display screen, the method comprising capturing a color image rendered on a display screen; and transforming the color image to binary color image, preserving text-like graphic components and filtering out non-text-like graphical components. The transforming comprises scanning one or more areas of the color image; and detecting continuous bi-tonal regions in the scanned one or more areas, wherein the continuous bi-tonal regions have large variances.

Abstract: A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.

Abstract: An apparatus for video to text conversion using video analysis, which analyzes at least one object included in video data input from a video acquisition device and provides motion information and attribution information of the object in the form of a sentence or word arrangement according to patterns. The apparatus includes an analysis unit, a generation unit, a database unit and a production unit.

Abstract: A method includes receiving a search query, identifying a document based on the search query, and providing a search result based on the document. The search result includes, for example, an image associated with the document, an excerpt from the document that is associated with the search query, and links to other excerpts in the document that are associated with the search query. The method may also include providing other information associated with the document.

Abstract: An information processing apparatus for processing print data includes an extracting unit that extracts characters to be printed and coordinate information of the characters from the print data; an organizing unit that reorganizes the characters extracted by the extracting unit using the coordinate information of the characters; a sorting unit that sorts the characters extracted by the extracting unit into corresponding horizontal or vertical lines using the coordinate information of the characters; and a concatenating unit that concatenates the characters reorganized by the organizing unit and sorted by the sorting unit.

Abstract: Processing a form in an image is provided. A plurality of data fields is detected within the form in the image. One or more of the data fields that contain private data and a plurality of the data fields that do not contain private data are detected. Contents of the plurality of data fields that do not contain private data are stored as metadata for the image and contents of the one or more data fields that contain private data are not stored as metadata for the image.

Abstract: An image forming apparatus includes: a scanner that obtains an image file by document scanning; a character recognition processor that obtains a text string from each line of text by performing character recognition; a text string splitter that splits each the text string into a plurality of short text strings in accordance with a predetermined rule; a font size determining portion that determines a uniform font size for each the text string; a position determining portion that determines x-axis positions for the short text strings on the basis of the x-coordinates of the characters at the forefront in the respective short text strings, the short text strings each having its x-axis in the forward and backward reading directions; and an embedding portion that embeds text data of the short text strings in the image file at the respective x-axis positions in the uniform font size for the entire text string.

Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.

Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.

Abstract: Systems and methods are provided for sharing a screen from a mobile device. For example, a method includes receiving an image from a mobile device, performing recognition on the image to identify space-delimited strings, and generating a content graph for the image, the content graph having content nodes that represent at least some of the strings and the content graph having edges that represent a relative position of strings associated with the content nodes connected by the edges. The method may also include repeating the receiving, performing recognition, and generating for a plurality of images, the plurality of images belonging to a session, and generating a combined graph from the plurality of content graphs based on similarity of content nodes between content graphs, the combined graph representing text from the plurality of images in reading order.

Abstract: Disclosed are various embodiments for a text module that receives, in at least one computing device, an encoded text block, the encoded text block comprising user generated text. A set of signals is identified in the encoded text block, each signal specifying a respective text unit, each text unit corresponding to a respective series of characters in the user generated text. The text module may render the user generated text and each series of characters in the user generated text. A text selection of a subset of one of the series of characters is initially prevented. The text module receives a selection of the text unit corresponding to the one of the series of characters, the selection of the text unit triggering a text selection of one of the series of characters.

Abstract: Metadata generated at the outset of an audio visual program, such as a television undergoes transmission to a field device associated with a capture device operated by production personnel, such as a news reporter and/or a videographer to capture one of audio and/or video information. The production personnel will typically edit the metadata for incorporation into the file structure of audio and/or visual information captured by the capture device. A server receives and updates the original metadata using the metadata in the file structure of the capture audio and/or video information, thus effectively harvesting the original metadata.

Abstract: A system, method and a computer program product for handling text distracters in a visual search have been disclosed. The system considers an image captured on a handheld device, as a query image and subsequently identifies the textual portions of the query image. The textual portions of the query image are smoothened in order to reduce the keypoints present in the textual portions. Non-textual portions in proximity to the textual portions are also selectively smoothened in order to prevent formation of an artificial border between the textual portions and non-textual portions. Further, the features are extracted from the non-textual portions of the query image are compared with the features of the images stored in a repository. An image whose features match with the extracted features is identified as an image relevant to the query image, and the identified image is transmitted, along with the associated metadata to the handheld device for display.

Abstract: A display control apparatus includes an image display that displays a document image representing a document file; an accepting unit that accepts an operation to point a portion in the document image displayed in the image display; an extracting unit that, upon acceptance of the operation to point the portion in the document image by the accepting unit, extracts each image portion surrounded by pixels other than white pixels from the entire document image if a ratio of the white pixels in the pixels in the document image is higher than or equal to a predetermined threshold value in an area of a predetermined size centered at the pointed portion; and a display controller that performs control so as to display information concerning the image portion having the shortest distance from the portion, among the image portions extracted by the extracting unit, in the image display.

Abstract: An electronic document generation apparatus extracts a processing target area including a row area from a scanned image of an original document and detects the dimensions of the row area, the row area being an area of either a whole or partial range of a row of character string arranged in one direction in the scanned image. The apparatus determines an arrangement-direction character size on the basis of the dimensions of the row area, and sends out image data of the processing target area and an instruction to perform OCR processing on the processing target area to an external apparatus. The apparatus then receives a processing result of the OCR processing from the external apparatus, and arranges a character string of the processing result in the electronic document on the basis of the arrangement-direction character size to generate an electronic document.

Abstract: The invention proposes a method for reconstructing a self-similar textured region of an image. Said method comprises determining pixels of a part of the self-similar textured region by copying sample pixels from a sample part of the self-similar textured region, the sample pixels being selected using a neighborhood matching, wherein a size of neighborhoods used for matching is selected based on an analysis of descriptors computed from coefficients of OCT transform of differently sized blocks of the sample part. The analysis of descriptors computed from coefficients of DCT transform of differently sized blocks of the sample part allows for determining the neighborhood size close to a feature size of the texture.

Abstract: A multi-orientation text detection method and associated system is disclosed that utilizes orientation-variant glyph features to determine a text line in an image regardless of an orientation of the text line. Glyph features are determined for each glyph in an image with respect to a neighboring glyph. The glyph features are provided to a learned classifier that outputs a glyph pair score for each neighboring glyph pair. Each glyph pair score indicates a likelihood that the corresponding pair of neighboring glyphs form part of a same text line. The glyph pair scores are used to identify candidate text lines, which are then ranked to select a final set of text lines in the image.

Abstract: A method for producing a photo album includes providing a library of page layouts, selecting a first group of one or more images to be placed in the first page of the photo album, selecting a second group of one or more images to be placed in the second page of the photo album, graphically displaying the first group of one or more images within a first border that represents a first page, graphically displaying the second group of one or more images within a second border that represents a second page, automatically selecting a first page layout from the library of page layouts, and automatically placing the first group of one or more images into the one or more image receiving areas in the first page layout to produce the first page in the photo album.

Abstract: A method includes tracking an object in each of a plurality of frames of video data to generate a tracking result. The method also includes performing object processing of a subset of frames of the plurality of frames selected according to a multi-frame latency of an object detector or an object recognizer. The method includes combining the tracking result with an output of the object processing to produce a combined output.

Abstract: A server system with one or more processors and memory obtains, from a client device, a card image which includes an image of a card, and identifies a card configuration type corresponding to the card in the card image based on a database of stored card configuration types. Each stored card configuration type in the database is associated with layout information regarding respective features and information regions for the stored card configuration type. In accordance with the identified card configuration type, the server system determines one or more information regions of the card image containing respective card information of the card. The server system extracts at least a portion of the card information of the card from the one or more information regions of the card image and transmits, to the client device, at least the extracted portion of the card information.

Abstract: A system for extracting and monitoring media tags within video content includes at least one server in communication with a plurality of content sources, the server receiving video content from the content sources, a recorder saving the video content, a detector receiving at least one frame of the video content, the detector detecting one or more unknown text within the frame and creating one or more images, each image associated with one of the one or more unknown text, the detector generating metadata associated with the one or more unknown text appearing in the frame, and an optical character recognition engine scanning the one or more images and converting the one or more images into one or more known text. The server further determines that the one or more known text is a media tag.