Abstract: A method of transferring a code of a structured document including background and at least one set of foreground and mask, to an image reproducing unit which reproduces the structured document code into a document image, includes, for each set of the foreground and mask, performing control to give priority to code of the mask over code of the foreground.

Abstract: A method for selecting a video thumbnail includes generating a visual theme model for a sample set of images that are representative of textual information corresponding to a video file. Each of a set of candidate key frames is distinguished according to similarities shared between the candidate key frames and the visual theme model. A display is caused of a selected one of the distinguished candidate key frames as a video thumbnail for the video file.

Abstract: An image forming apparatus capable of automatically creating an index, and a method for the same. The image forming apparatus includes a scan unit to scan a document, a text/image separation unit to separate the scanned document into a text area and an image area and to separate texts in the text area into symbols, an index determination unit to extract one or more properties of the separated symbols and to compare the extracted symbol properties with one or more index thresholds to determine whether text including the symbols is an index object, and an index page creation unit to create an index page including the text determined as the index object and information about a page including the text that corresponds to the index object. Accordingly, since the index page is automatically created, main contents of each page of the document can be easily selected and/or presented.

Abstract: Systems and methods for segmenting an image into at least two layers, a foreground and a background layer include rough labeling or segmenting at least a portion of the image into foreground and background pixels. The rough labeled pixels may be refined by using local classifications. Additional processes may be performed on the image including, but not limited to, filtering, image enhancing, shape refining, image compression, etc.

Abstract: Disclosed are embodiments of systems and methods for eliminating or reducing the distortion in a scanned image. Embodiments of the present invention allow for the automatic pruning, de-skewing, and unwarping of an image using document layout information. In embodiments, dominant baselines may be selected by examining the letter regions on boundary baselines rather than examining the entire document layout. The dominant baselines may then be used to reduce distortion in the image. It shall be noted that present invention is robust enough to handle many types of content, including different languages, as well as documents with different layouts. The present invention may also be applied to images obtained from bound documents and flat documents.

Abstract: A system and method to identify pictures in documents. An image representing a page of a document is received. The image is analyzed to identify text objects in the page. A masked image is generated by masking out regions of the image including the text objects in the page. Groups of pixels in the masked image are identified, wherein a respective group of pixels corresponds to at least one picture in the page. When there is one or more groups of pixels, regions for pictures are identified based on the one or more groups of pixels. Metadata tags for the pictures are stored, wherein a respective metadata tag for a respective picture includes information about a respective bounding box for the respective picture.

Abstract: The present invention relates to systems and methods for analyzing media material having articles continuing across multiple pages. A media material analyzer includes a segmenter and an article composer. The segmenter identifies block segments associated with columnar body test in the media material. The article composer determines which of the identified block segments belong to a continuing article extending across multiple pages in the media material based on language statistics information and continuation transition information.

Abstract: An apparatus usable in an image encoding and decoding system includes segmentation unit to divide an image into one or more blocks, to segment the blocks into a binary mask layer of a foreground and a background according to a cost optimized function and a feature vector to generate a segmentation image according to the segmented blocks.

Abstract: A method capable of detecting a scoreboard in a program includes detecting a region which displays static images in a program having a plurality of frames, identifying the text contents of the region, and determining whether the variation in the text contents is larger than a predetermined value and occurs conforming to a predetermined rule. If the variation in the text contents is larger than the predetermined value and occurs conforming to the predetermined rule, the method signifies that the region displays the static images corresponding to a scoreboard.

Abstract: An information processing device includes: a document receiving unit that receives a document containing at least one page, wherein positions of document components of a page of the at least one page are fixed within the page; a page dividing unit that divides the document received by the document receiving unit into at least one page; a page heading determining unit that determines a heading of a page of the at least one page divided by the page dividing unit based on components included in the page; and a processing unit that assigns the heading determined by the page heading determining unit to the page divided by the page dividing unit as first level outline information of the page.

Abstract: A system is disclosed that can find an image of a foreground object in a still image or video image. Finding the image of the foreground object can be used to reduce errors and reduce the time needed when creating morphs of an image. One implementation uses the detection of the image of the foreground object to create virtual camera movement, which is the illusion that a camera is moving around a scene that is frozen in time.

Abstract: Embodiments of the present invention comprise systems, methods and devices for detection of image regions of various content types using a masking condition and an entropy measure.

Abstract: A visualization program, method and apparatus for determining reading order of content in a structured document. The method includes generating, for each of a plurality of elements, a directed segment; storing, in the reading order, the generated directed segments of the elements into a storage device; reading from the storage device; linking together the directed segments for the elements in accordance with the reading order; and displaying the linked directed segments overlaid on the structured document which is displayed on the screen. A computer implemented program and an apparatus for carrying out the above method are also provided.

Abstract: A method and system for analysis of immunoassays, and more specifically to an improved analysis of chromatographic assays, often referred to as a lateral flow assay is disclosed. These assays commonly employ a test strip utilizing visible particles as the labels for the analytes to be detected, where, as an additional feature, the analytical strip is removable for reading the quantity of analytes captured therein and for archival purposes. An image of the test strip is analysed automatically.

Abstract: Aspects of the present invention relate to systems, methods and devices for detection of text in an image using an initial text classification result and a verification process. In particular, a support region of a candidate text pixel in a text-candidate map may be expanded to produce a revised text-candidate map. Pictorial regions in the image may be discriminated based on an entropy measure using masking and the revised text-candidate map, and the revised text-candidate map may be refined based on the pictorial regions.

Abstract: Remote deposit of checks can be facilitated by a financial institution. A customer's general purpose computer and image capture device may be leveraged to capture an image of a check and deliver the image to financial institution electronics. Additional data for the transaction may be collected as necessary. The transaction can be automatically accomplished utilizing the images and data thus acquired.

Abstract: Methods and systems of the present embodiment provide segmenting of connected components of markings found in document images. Segmenting includes detecting aligned text. From this detected material an aligned text mask is generated and used in processing of the images. The processing includes breaking connected components in the document images into smaller pieces or fragments by detecting and segregating the connected components and fragments thereof likely to belong to aligned text.

Abstract: A method and system reconstructs a contone image from a binary image by first tagging pixels to identify one of a multiplicity of image content types. The tag information and the pattern of bits surrounding the pixel to be converted to a contone value are used to reconstruct a contone image from a binary image. The pattern of bits in the neighborhood is used to generate a unique identifier. The unique identifier is used as the address for a lookup table with the contone value to be used. A filter also generates a contone value. A selector selects between the look-up table contone value and the filter contone value based an image context type.

Abstract: Aspects of the present invention relate to methods and systems for segmenting a digital image into regions. A frequency-of-occurrence of image values may be determined excluding a portion of pixels in a digital image. An image value associated with a peak in the frequency-of-occurrence of image values may be identified and associated with an image label. Pixel locations may be labeled based on the associated labels and image values. Additionally, unreliable pixels may be determined and labeled based on the associated labels and image values.

Abstract: A system and method for storing, associating and displaying transcriptions and translations of text presented in video segments.

Abstract: This invention provides an image processing system and image processing method which allow a user to easily confirm conversion result information when image information is converted into vector data. Image information input from an input device (113) is vectorized by a data processing device (115). Vector data which has successfully been vectorized is converted into image data. The input image information and the converted image data are combined to generate and output combined image data.

Abstract: In an embodiment, hidden graphical elements in a graphic are detected by generating a first bitmap based on a plurality of graphical elements and a second bitmap based on a first subset of the plurality of graphical elements where the first subset omits a first graphical element of the plurality of elements and includes a second graphical element of the plurality of elements. The first bitmap is then compared with the second bitmap to determine if they match. If they match, the first graphical element is considered to be hidden by the second graphical element.

Abstract: An image processing method according to the present invention includes extracting from a document image an area to be determined, calculating the number of closed loops within the extracted area, and making a determination based on the calculated number of closed loops, whether the area is a character area. This invention makes it possible to determine with a high accuracy whether an area to be determined is a character area.

Abstract: A method of identifying regions of different content in an image comprises dividing image data into a plurality of pixel blocks, extracting features of the pixel blocks and classifying the content of the pixel blocks based on extracted features. Extracting comprises, for each pixel block, convolving a magic square filter with the pixels of the pixel block and summing the results, and calculating the percentage of background pixels in the pixel block. The magic square filter is a 3×3 kernel that has a specific selectivity towards the statistical appearance and geometric alignment of a document based text of various fonts, sizes and styles. The complete sum of the magic square filter, as well as the sum of the rows, columns and diagonals of the magic square filter are zero.

Abstract: An apparatus and method generate encoded data including lossless- and lossy-encoded data together within a unit time period while fully using the lossy encoding processing capability, by appropriately setting a threshold associated with the number of tiles. To this end, an image encoding apparatus has a lossless encoding processing unit and a lossy encoding processing unit. The lossless encoding processing unit outputs one of lossless-encoded data and non-encoded data from a selection unit to a memory based on the attribute information for each tile. Every time the total data size of non-encoded data output from the selection unit exceeds a predetermined threshold, a resolution converting unit executes processing for decreasing the resolution of the non-encoded data in the memory. Upon completion of storage of data for one page in the memory, a lossy encoding unit begins to generate lossy-encoded data from the non-encoded data.

Abstract: A method for transforming Video-To-Text is disclosed that automatically generates text descriptions of the content of a video. The present invention first segments an input video sequence according to predefined semantic classes using a Mixture-of-Experts blob segmentation algorithm. The resulting segmentation is coerced into a semantic concept graph and based on domain knowledge and a semantic concept hierarchy. Then, the initial semantic concept graph is summarized and pruned. Finally, according to the summarized semantic concept graph and its changes over time, text and/or speech descriptions are automatically generated using one of the three description schemes: key-frame, key-object and key-change descriptions.

Abstract: A system for processing a visual capture operation as described. The system receives an indication of a visual capture operation performed from a rendered document. The indication specifies both a text sequence capture as part of the capture operation and a supplemental marking captured as part of the capture operation. The system determines an action to perform in response to receiving the indication, based both upon the text sequence specified in the indication and the supplemental markings specified by the indication.

Abstract: This invention relates to a method for calculating and adjusting photo and text separation performance. The method for calculating photo and text separation performance comprises a step of generating a standard block attribute file and a step of comparing a photo and text separation result with the standard block attribute file so as to display a photo and text separation performance table. The method for adjusting photo and text separation performance comprises a step of comparing a photo and text separation result with the standard block attribute file to generate the photo and text separation performance table, and a step of according to the photo and text separation performance table to decide whether to use another photo and text separation algorithm or parameters to perform another photo and text separation.

Abstract: A method and apparatus for detecting text in real-world images comprises calculating a cascade of classifiers, the cascade comprising a plurality of stages, each stage including one or more weak classifiers, the plurality of stages organized to start out with classifiers that are most useful for ruling out non-text regions, and removing regions classified as non-text regions from the cascade prior to completion of the cascade, to further speed up processing.

Abstract: A video processing method for selectively processing character information (Ic) included in an inputted video stream (Svc). The video stream (Svc) is separated in units of frame into a brightness frame (Y) representing brightness information (VY) and a plurality of color difference frames (Cb, Cr) representing color difference information (VCb, VCr). Character information (Ic) included according to at least either of the brightness information (VY) and the color difference information (VCb, VCr) is recognized. The recognized character information (Ic) is subjected to a processing by at least one of deletion, movement, and enlargement.

Abstract: An automatic word segmentation and glyph variation system and method are provided herein.

Abstract: The present invention relates to a signal processing device which learns operations made by a user without the user knowing, and which can perform processing optimal to the user based on the learning results. At a learning unit 22, operating signals supplied according to user operations are monitored, and judgment is made whether or not these can be used for learning. In the event that the operating signals are learning operating signals which can be used for learning, the learning unit 22 learns a correction norm which is the norm for correcting input signals, based on the learning operating signals. On the other hand, at a correcting unit 21, post-correction signals, wherein the input signals are corrected based on the correction norm obtained by learning, are output as output signals. The present invention can be applied to an NR (Noise Reduction) circuit which removes noise.

Abstract: A method is claimed for processing a vector-raster image file which contains a text image. The method comprises the steps of: fragmenting the image to obtain regions containing non-separable, logically connected fragments of text of the maximum possible size; processing text, vector, and raster objects; discarding excessive information; analyzing each object with the help of all available information. The step of processing text objects includes the steps of: dividing into separate characters and character groups according to supposed locations of blank spaces or other non-indicated symbols, and analyzing and assembling character groups into words and verifying and correcting characters encoding based on recognition of assembled words as raster objects. The step of processing vector objects includes the step of identifying separators, background, and substrates of blocks.

Abstract: A portable terminal apparatus consecutively more than once captures images of an identical image capture object. The portable terminal apparatus determines whether or not a plurality of pieces of captured image data captured include a combination of a given number (an integer not less than 2) of pieces of captured image data which are applicable to be subjected to the high resolution correction by the correction processing section and are offset by a given amount, and transmits, to an image output apparatus, the given number of pieces of captured image data which are determined to be the combination. The image output apparatus receives the given number of pieces of captured image data from the portable terminal apparatus, and carries out, in accordance with the given number of pieces of captured image data, the high resolution correction for preparing high resolution image data which has a higher resolution than the given number of pieces of captured image data received.

Abstract: An image output apparatus receives a single piece of captured image data from a portable terminal apparatus, and carries out, in accordance with the single piece of captured image data received, a high resolution correction for creating high resolution image data which has a higher resolution than the single piece of captured image data. Then, the image output apparatus carries out an output process in which the high resolution image data created is outputted. This provides a captured image processing system which allows an image output apparatus to output an image captured by a portable terminal apparatus while the image is improving in resolution such as text readability.

Abstract: Methods and apparatus for detecting moving text in video comprising receiving consecutive frames from a video stream, extracting a sequence of pixels from the consecutive frames, categorizing the pixels, thinning the pixels, correlating corresponding thinned pixels in the frames, identifying the peaks that are equal to or exceed a threshold, and performing further processing on the peaks to determine if the peaks contain moving text.

Abstract: Image forming apparatus, which prevents the occurrence of displacement of the positions of pixels between image data items forming a synthetic image, and eliminates distortion of a character and color shift in character regions and non-character regions. An image size adjustment section obtains, when synthesizing a plurality of image data items to create one image, a remainder by dividing the number of vertical and horizontal pixels of input image data by a least common multiple of the ratio of resolutions of a plurality of image data items, for vertical and horizontal directions of the image. The input image data is processed by means of the result of computing the remainder, so that the remainder becomes 0 when obtaining the remainder by dividing the number of vertical and horizontal pixels of the input image data by the least common multiple of the ratio of the resolutions of the image data items.

Abstract: A method for optimizing a source document comprising a plurality of pages of content, comprising each of the following, is presented. A source document is obtained. An optimized document is created corresponding to the source document. Thereafter, for each page in the source document, the following are applied. A page record is created for the page. Each page record comprises a word table comprising a list of the page's words in the order that they appear in the page's content. Each page record further comprises a paragraph entry list for the page including a paragraph entry for each paragraph in the page. Each paragraph entry includes a reference to the first and last word of that paragraph in the word table. The page record is compressed using a compression technique. Thereafter, the compressed page record is stored in the optimized document.

Abstract: An embodiment provides for enabling retrieval of a collection of captured images that form at least a portion of a library of images. For each image in the collection, a captured image may be analyzed to recognize information from image data contained in the captured image, and an index may be generated, where the index data is based on the recognized information. Using the index, functionality such as search and retrieval is enabled. Various recognition techniques, including those that use the face, clothing, apparel, and combinations of characteristics may be utilized. Recognition may be performed on, among other things, persons and text carried on objects.

Abstract: An image scanning system includes (1) an image scanning device, which includes an input unit configured to acquire an instruction by a user, an image scanner configured to scan an image and generate image data and a transmitting unit configured to transmit the image data; (2) a display lock judging unit configured to judge whether a display lock is necessary based on whether a predetermined instruction is acquired by the input unit; and (3) a data processing device which includes a first reception unit configured to receive the image data transmitted by the transmitting unit of the image scanning device, a first display unit configured to display the image data received by the first reception unit and a display control unit configured to control the first display unit so as not to display the image data if the display lock judging unit judges that the display lock is necessary.

Abstract: An apparatus and method for generating additional information about moving picture content, including: comparing image feature information about each image frame in moving picture content with image feature information about each image frame in web information, searching for an image frame in the moving picture content, the image frame matching the image frame in the web information, determining location information about the found image frame in the moving picture content, and generating additional information by use of the determined location information and the web information.

Abstract: A fingerprint of an image identified within a received message is generated following analysis of the message. A spam detection engine identifies an image within a message and converts the image into a grey scale image. The spam detection engine analyzes the grey scale image and assigns a score. A fingerprint of the grey scale image is generated based on the score. The fingerprint may also be based on other factors such as the message sender's status (e.g. blacklisted or whitelisted) and other scores and reports generated by the spam detection engine. The fingerprint is then used to filter future incoming messages.

Abstract: An image processing apparatus includes: a recognition process section for performing, on the basis of image data of a document, a character recognition process of recognizing a character contained in the document; a chromatic text generation section for generating color text data (character image data) indicative of character images in which character images with different attributes are displayed with different colors; and an image composition section for generating composite image data by combining the image data of the document with the color text data so that each of the character images indicated by the color text data is partially superimposed on a corresponding image of a character in the document. The image processing apparatus causes a display device to display an image in accordance with the composite image data. This allows a user to easily check whether or not a result of the character recognition process is correct.

Abstract: A technique is described for table grid detection and separation during the analysis and recognition of documents containing table contents. The technique includes the steps of table detection, grid separation, and table cell extraction. The technique is characterized by the steps of detecting the grid lines of a table using, for example, inverse cell detection, separating noise and touching text from the grid lines, and extracting the cell contents for OCR recognition.

Abstract: The present invention allows a thumbnail display representing the outline of input images in a digital image printer to be made, in which it is determined whether an image is a first kind of image or a second kind of image, and if it is determined that the image is the first kind of image, a feature part of the first kind of image is enlarged in the thumbnail display to make the contents of image more understandable. Also, the invention allows a thumbnail display representing the outline of input images in a digital image printer to be made, in which it is determined whether an image is a character image or a gradation image, and if it is determined that the image is the character image, a part of the character image is enlarged in the thumbnail display to make the characters more understandable.

Abstract: Structural content filtration to reduce the number of hypotheses for the location of an active object in a recorded image generated by a graphical user interface (GUI) of an application program may be accomplished by transforming the recorded image and a corresponding playback image, determining a sub-image from the transformed recorded image which corresponds to an object to be searched for in the transformed playback image, determining a set of points on the transformed playback image which have appropriate values for matching the sub-image, and filtering hypotheses on the playback image which are more than a selected distance from any one of the subset of points.

Abstract: A character recognition device includes: an acquiring unit that acquires image data describing pixel values representing colors of pixels constituting an image; a binarizing unit that binarizes the pixel values; an extracting unit that extracts boundaries of colors in the image; a delimiting unit that delimits plural image areas in the image; a specifying unit that specifies, with regard to first image areas arranged according to a predetermined rule, pixels binarized by the binarizing unit, as a subject for character recognition, and specifies, with regard to second image areas not arranged according to the predetermined rule, pixels of areas surrounded by boundaries extracted by the extracting unit, as a subject for character recognition; and a character recognition unit that recognizes characters represented by the pixels specified by the specifying unit as a subject for character recognition.

Abstract: An apparatus and method for processing a captured image and, more particularly, for processing a captured image comprising a document. In one embodiment, an apparatus comprising a camera to capture documents is described. In another embodiment, a method for processing a captured image that includes a document comprises the steps of distinguishing an imaged document from its background, adjusting the captured image to reduce distortions created from use of a camera and properly orienting the document is described.

Abstract: The present invention relates to systems and methods for analyzing media material having a layout. A media material analyzer includes a segmenter and an article composer. The segmenter identifies block segments associated with columnar body text in the media material. The article composer determines which of the identified block segments belong to one or more articles in the media material. The article composer can determine whether candidate block segments belong to a same article based on language statistics information, layout transition information, or both language statistics information and layout transition information. A system for searching media material having a layout over a network is also provided.

Abstract: In an image forming system in which a printing device is communicably connected to a server and a terminal, an automatic determination is performed to determine whether or not print data created by the terminal needs to be stored in a memory for placing the data in a reprintable condition. The print data stored in the memory can be reprinted without need for resending the same print data from the terminal or server to the printing device. The automatic determination is, for example, performed by referring to the header of the print data and determining whether the print data is from the terminal or the server.