Abstract: Attribute information accessory to a pixel can be used to determine whether to execute an interpolation process of less than one pixel at a scan line changing point in color misregistration compensation for a printout from an image forming apparatus having a characteristic shifted in the laser scanning direction for each color. When the attribute information is an attribute representing execution of the interpolation process of less than one pixel, it is enlarged in the sub-scanning direction. Attribute information of each color component can be generated from attribute information accessory to a pixel by using the attribute information accessory to the pixel, and each color component value which forms the pixel.

Abstract: The present invention provides a technique of accurately extracting areas of characters included in a captured image. A character extracting device of the present invention extracts each character in an image with compensated pixel values. In more detail, the character extracting device integrates pixel values at each coordinate position in the image along a character extracting direction. Then, the character extracting device predicts the background area in the image based on the integrated pixel value. The compensated pixel values are compensated based on integrated pixel values at the predicted background area from integrated pixel values at each coordinate position.

Abstract: An image processing apparatus segments Western and hieroglyphic portions of textual lines. The apparatus includes an input component that receives an input image having at least one textual line. The apparatus also includes an inter-character break identifier component that identifies candidate inter-character breaks along a textual line and an inter-character break classifier component. The inter-character break classifier component classifies each of the candidate inter-character breaks as an actual break, a non-break or an indeterminate break based at least in part on the geometrical properties of each respective candidate inter-character break and the bounding boxes adjacent thereto. A character recognition component recognizes the candidate characters based at least in part on a feature set extracted from each respective candidate character that can be histogram features, Gabor features or any other feature set applicable to character recognition.

Abstract: An image display apparatus is disclosed that includes an image projecting unit that projects a projection image on a projection screen, a written image capturing unit that captures a written image of a writing screen that is arranged opposite the projection screen, a written image area extracting unit that extracts a written image area from the captured written image captured by the written image capturing unit, an image compositing unit that composites the written image area extracted by the written image area extracting unit and the projection image projected by the image projecting unit. The written image area extracting unit includes an external light value detecting unit that detects an external light value and an image processing unit that performs an image correction process on the captured written image based on the external light value detected by the external light detecting unit.

Abstract: The method, system, and apparatus of source statistics based intra prediction type is disclosed. In one embodiment, a method includes classifying a four-pixel square block in an edge class (e.g., may include a DC edge class, a vertical edge class, a horizontal edge class, a diagonal edge class, and/or a planar edge class) based on an edge classifier, classifying an eight-pixel square block having the four-pixel square block and other four-pixel square blocks as a homogenous class if the four-pixel square block and the other four-pixel square blocks of the eight-pixel square block belong to the edge class, assigning a direction to the edge class of the eight-pixel square block, and determining an optimal intra-prediction type through the classification such that empirical testing of all possible ones of the edge class and the direction is avoided when the homogenous class is identified.

Abstract: Methods, systems, and apparatus including computer program products for recognizing text in images are provided. In one implementation, a computer-implemented method for recognizing text in an image is provided. The method includes receiving a plurality of images. The method also includes processing the images to detect a corresponding set of regions of the images, each image having a region corresponding to each other image region, as potentially containing text. The method further includes combining the regions to generate an enhanced region image and performing optical character recognition on the enhanced region image.

Abstract: Even when captions of a plurality of objects use an identical anchor expression, the present invention can associate an appropriately explanatory text in a body text as metadata with the objects.

Abstract: A method and system is provided for identifying a page layout of an image that includes textual regions. The textual regions are to undergo optical character recognition (OCR). The system includes an input component that receives an input image that includes words around which bounding boxes have been formed and a text identifying component that groups the words into a plurality of text regions. A reading line component groups words within each of the text regions into reading lines. A text region sorting component that sorts the text regions in accordance with their reading order.

Abstract: An image processing method includes the following steps. Firstly, a specified digital image and a designated text/graph are retrieved. Then, the specified digital image is processed to obtain image information associated with a right-side-up image of the specified digital image. Afterwards, the designated text/graph is automatically adjusted and attached on a specified position relative to the right-side-up image according to the image information, thereby printing the specified digital image and the designated text/graph.

Abstract: A logical structure analyzing apparatus includes an extracting unit that extracts word candidates from a form, a first generating unit that classifies each of the word candidates into a group of heading candidates or a group of data candidates to generate, based on positions of the word candidates on the form, first candidates sets each including one heading candidate and one data candidate identifiable by the heading candidate, and a second generating unit that combines the first candidate sets to generate second candidate sets that each include plural heading candidates that differ and one data candidate. The apparatus also includes a removing unit that, based on positions of the heading candidates and the data word candidate in each second candidate set, removes from among the second candidates sets, a determined set including a data item and headings identifying the data item, and an output unit that outputs the determined set.

Abstract: Method for up-scaling a color image prior to performing subsequent processing on said color image, comprising the steps of converting the color image into multiple image layers distinguishable from each other and up-scaling at least one of said multiple image layers. The up-scaling is tuned towards the subsequent processing, for example luminance is upscaled at higher quality than chrominance. Further, a method for interpreting information present on digitally acquired documents, comprising the steps of: (i) determining a country; (ii) identifying a list of languages and character sets in use in said country; (iii) performing optical character recognition simultaneously using all languages and character sets of the list; (iv) performing field parsing to identify fields in the digitally acquired document on the basis of international as well as country-specific field recognition rules; (v) storing the recognized information according to the identified fields in a database.

Abstract: This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

Abstract: An image forming apparatus is provided which includes: an image acquisition section (110) which reads an original and acquires an original image; a specific-pattern storage section (141) which stores a specific pattern which expresses, using a dot pattern, apparatus identification information for identifying an apparatus that prints the original image on a sheet of recording paper; an extraction section (132) which extracts an actual image area except a blank area in the original image, and base on the extracted actual image area, extracts a specific area corresponding to an area for printing the specific pattern; and a print section (150) which prints the specific pattern within the actual image area, using a yellow toner.

Abstract: A method, system, and computer program product for font reproduction in electronic documents are provided. The method includes: receiving an image of a printed document; extracting pairs of consecutive characters from the image of the printed document; storing the extracted pairs as images of the characters; and reproducing the printed document as an electronic document with text of overlapping extracted character pair images. Extracting pairs of consecutive characters includes extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters. Reproducing the printed document as an electronic document includes reproducing the spacing between words and between lines using the spaced horizontal characters and the spaced vertical characters as anchors in the reproduced document.

Abstract: A document authentication method compares a target document image (scanned image) with an original document image at multiple levels, such as block (e.g. paragraph, graphics, image), line, word and character levels. The paragraph level comparison determines whether the target and original images have the same number of paragraphs and whether the paragraphs have the same sizes and locations; the line level comparison determines if the target and original images have the same number of lines and whether the lines have the same sizes and locations; etc. Document segmentation is performed on the target and original images to segment them into paragraph units, line units, etc. for purposes of the comparisons. The original document may be segmented beforehand and the segmentation information stored for later use. The authentication process may be designed to stop when alterations are detected at a higher level, so lower level comparisons are not carried out.

Abstract: Embodiments of the present invention recite a system and method for creating an editable template from a document image. In one embodiment of the present invention, the spatial characteristics and the color characteristics of at least one region of a document are identified. A set of characteristics of a graphic representation within the region are then determined without the necessity of recognizing a character comprising the graphic representation. An editable template is then created comprising a second region having the same spatial characteristics and the same color characteristics of the at least one region of the document and comprising a second graphic representation which is defined by the set of characteristics of the first graphic representation.

Abstract: Aspects of the present invention relate to systems and methods for refining text segmentation results. Non-text, line elements in a text map may be detected and removed from the text map. Pixels associated with vertical and/or horizontal lines may be identified in the text map based on a background-color constraint, a directional color constraint and a continuity constraint. Run counters and run-reset counters associated with a direction may be used to identify pixels meeting the continuity constraint.

Abstract: A method for storing a document recognition result is proposed. The method includes selecting a picture area from a document image, storing an image of the selected picture area in an image file format, removing the selected picture area, filling the removed picture area with a surrounding background color, and performing character recognition of a text area.

Abstract: An image processing device includes: an acquisition section that acquires subject image information to be formed on a medium; an extraction section that selectively extracts a part of the subject image information corresponding to a portion of an image not formed due to a plurality of holes of a medium if an image relating to the subject image information is formed on the medium perforated with the plurality of holes; and a generation section that generates new subject image information by generating a command for forming the extracted part of the subject image information.

Abstract: The class of a sheet is efficiently estimated and a pattern identification process which is robust to a variation in the medium can be performed by dividing an image pattern of the sheet into a plurality of areas (pixels or sets of pixels), weighting and selecting the areas, attaining the identification results for the respective areas and determining the identification result of the whole portion based on a logical combination of the identification results. Particularly, since the area weighting and selecting process is performed based on a difference between the classes and a variation in the class, the calculation amount can be reduced and the identification performance which is higher than that of a method which uniformly processes the whole portion of the pattern can be attained.

Abstract: Disclosed are embodiments of systems, devices, and methods to reduce compression artifacts in multi-layer images. Pixel dilation operations, such as morphological dilations, are performed to identify unlabeled pixels at boundaries between layers, and the colors of those pixels are adjusted to mitigate formation of artifacts during layer compression.

Abstract: The present invention decides whether an OCR processing is necessary or not for a printing job by using a difference between text data extracted by performing the OCR processing on an image generated based on a previous printing job having been processed previously and text data extracted from text drawing command of the previous printing job having been processed previously. If the OCR processing is decided to be unnecessary, the text data extracted from the text drawing command of the printing job is registered in a database for retrieving an image data. If the OCR processing is decided to be necessary, text data extracted by performing OCR processing on the image data generated based on the drawing commands of the printing job and the text data extracted from the text drawing command of the printing job are registered in a database for retrieving an image data.

Abstract: A system for segregating handwritten information from typographic information on a document may include a memory, an interface, and a processor. The memory stores an electronic document image of a document where the electronic document image includes pixels and each pixel has a characteristic. The processor may receive, via the interface, the electronic document image and may identify first, second and third most frequently occurring characteristics of the pixels of the electronic document image. The pixels having the first most frequently occurring characteristic represent a background of the document. The processor may determine the typographic information of the document as represented by pixels having the second most frequently occurring characteristic. The processor may determine the handwritten information of the document as represented by pixels having the third most frequently occurring characteristic.

Abstract: An image processing apparatus includes a binarizing unit, a determining unit, a counting unit, and a correcting unit. The binarizing unit binarizes image data based on density of the image data. The determining unit determines a pixel with high density as a character pixel and a pixel with low density as a non-character pixel in the binarized image data. The counting unit counts the number of a sequence of character pixels in a scanning direction. The correcting unit corrects, when the number of the sequence of the character pixels exceeds a threshold value, the character pixels to non-character pixels.

Abstract: An image-data-acquisition control unit controls an image-data acquiring unit that acquires computer-recognizable image data, to accumulate the image data in a set of information units. A character-recognition control unit controls an optical character-recognizing unit that extracts a character from the set of image data accumulated by the image-data-acquisition control unit, to accumulate a group of characters obtained by the optical character-recognizing unit in a set of character information units. Once a start signal is received from a starting unit, the image-data-acquisition control unit and the character-recognition control unit continue to operate independently.

Abstract: A decomposition specification is received. The decomposition specification includes specifications of locations of text line images corresponding to complete lines of text in a document image. Based on the decomposition specification, a layout of the text line images in respective lines of a reflow area is generated, where each of the lines of the reflow area has a respective maximum line length. In this process, successive ones of the text line images are packed onto the lines of the reflow area with divisions of one or more of the text line images into respective portions that are concatenated with text image content of other ones of the text line images to fill respective ones of the lines of the reflow area without exceeding the respective maximum line lengths.

Abstract: A text recognition region detecting apparatus and a text recognition method are provided. A text recognition region is detected by expanding a region based on a user-specified position that is input through a simple manipulation by a user. A text recognition is performed on the detected text recognition region, thereby relieving a user from having to precisely input the text region and ensuring the user's convenience.

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: In an image forming apparatus and a data transmission method thereof, text data are extracted and transmitted for the purpose of the security management of data so that time and management cost of security violation are reduced. The image forming apparatus for security transmission of data includes a text extractor to extract text data from the data and a transmitter to transmit the text data to a management server to obtain transmission permission and then to transmit the data to a transmission target.

Abstract: An image processing device includes a processor controlling one or more components of the image processing device, a region extraction unit for separating and extracting a character region, a graphic region and a photograph region from image data; a region compression unit for performing a compression process for each of the region data extracted by the region extraction unit; a region synthesis unit for synthesizing the region data compressed by the region compression unit; and an image size calculation unit for calculating an image size of specific region data extracted by the region extraction unit. The region compression unit selectively uses a first compression method or a second compression method to perform the compression process for the specific region data.

Abstract: A binary image is generated by binarizing a multilevel image. An edge image is generated by extracting an edge component in the multilevel image. The binary image is segmented into a plurality of regions with different attributes. An outline candidate of a halftone region is extracted from the edge image. A second region segmentation result is output on the basis of the information of the outline candidate and information of the region segmentation result.

Abstract: A method consistent with certain embodiments of identifying a functional command set for an access device that accesses television programming provided by a service provider at a control device involves transmitting a first command from a first command set of a group of possible command sets for the access device to the access device. The first command includes a command that is expected to cause the access device to generate a text containing video frame. A determination is made as to whether the extracted text corresponds to the first command set. The first command set is identified as the functional command set for the access device in response to determining that the extracted text corresponds to the first command set. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.

Abstract: A system for electronically distilling information from a business document uses a network scanner to electronically scan a platen area, having a business document thereon, to create a bitmap. A network server carries out a segmentation process to segment the scan generated bitmap into a bitmap object, the bitmap object corresponding to the scanned business document; a bitmap to text conversion process to convert the bitmap object into a block of text; a semantic recognition process to generate a structured representation of semantic entities corresponding to the scanned business document; and a document generation process to convert the structured representation into a structure text file.

Abstract: A system and process for harvesting context information from selected content is described. One may use a stylus to indicate what content is to be captured. The context information that may be associated with selected content may include URLs, file names, folder names, text from the content, and ink.

Abstract: A value of a selection parameter is sequentially set from among a plurality of parameters included in a modeling equation to derive a quantization matrix. A value of each of the parameters is sequentially derived based on a code amount and an encoding distortion obtained from an encoding using a quantization matrix generated from an updated parameter set.

Abstract: A computer-implemented method is provided for creating an image-based reflowable file. The image-based reflowable file is configured to automatically adapt itself to be rendered on various sized displays and windows, by permitting the lines of reflow objects to “reflow” according to the given size of a display or window. The method includes receiving. First, an image of content having reflow objects and identifying bounding regions to enclose a reflow object contained in the image. A reflow object baseline for each of the reflow objects is then identified and the position of each of the bounding regions containing the reflow objects is determined, relative to the image and also relative to the corresponding reflow object baseline. The size of each of the bounding regions is then determined, for example in terms of width and height, and stored.

Abstract: A computer system and method for efficiently processing a digital image into reflow content is presented. The method comprises each of the following as executed on a computer. A digital image is obtained for processing. The digital image includes at least some content suitable for conversion into reflow content. The digital image is processed into a digital content file. The digital content file includes both reflow content and non-reflow blocks of content. For each non-reflow block of content in the digital content file, the following are performed. A confidence rating is determined for the non-reflow block of content. If the confidence rating for the non-reflow block of content falls below a predetermined threshold, an evaluation of the non-reflow block is triggered.

Abstract: Dropping out of color form backgrounds from images of completed forms to obtain color form dropout images retaining only the respondent information. In one embodiment, a color form image processing method (100) includes retrieving (102) a template image, retrieving (104) a respondent image, registering (106) the images against one another to establish correspondence between pixels in the respondent and template images, dilating (108) the template image, and performing (110) a color form dropout including comparing (112) corresponding pixels in the respondent and dilated template images, and determining (114) whether to keep corresponding pixels by applying (116) a geometric solid threshold comparison to assess both color similarity and relative darkness, and removing (118) pixels from the respondent image based on such comparison.

Abstract: Methods, systems, and apparatus including computer program products for enhancing text in images are provided. In one implementation, a computer-implemented method is provided. The method includes receiving a plurality of images each image including a corresponding version of an identified candidate text region and aligning each candidate text region from the plurality of images to a high resolution grid. The method also includes compositing the aligned candidate text regions to create a single superresolution image and performing character recognition on the superresolution image to identify text.

Abstract: A character recognition device to recognize characters after preprocessing an input image corrects distortion. The character recognition device includes an image input unit to receive an image acquired by an image device, a character position estimator to calculate a probability value of a position of characters of the image to estimate the position of the characters, an image preprocessor to detect a plurality of edges including the characters from the image and to correct distortion of the edges, and a character recognizer to recognize the characters included in a rectangle formed by the plurality of edges.

Abstract: An image processing method, for receiving an input image and separating pixels having text characteristics and pixels having figure characteristics, includes: applying a first filtering processing for the input image to derive a first image processing result; applying a second filtering processing for the first image processing result to derive a second image processing result, wherein a distribution of filtering parameters of the first filtering processing is different from a distribution of filtering parameters of the second filtering processing; deriving a set of first reference values according to the first image processing result and the second image processing result; and determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the first reference values and a predetermined threshold.

Abstract: Imposition system and drivers for printer products prepare a document for printing by receiving an electronic document to be printed, determining a smallest font size of the text of at least a portion of the document; determining a scale factor for at least one portion of the document based on the smallest font size and a predetermined minimum font size; and scaling at least a portion of the document by the scale factor.

Abstract: After markings have been placed on a pre-printed form by a user who interacted with an entity, the form is scanned to produce a scan file. The scan file is analyzed to identify whether user added markings are present on machine readable selection items. The method can take a number of automated actions, depending upon which pre-printed machine readable selection items were checked by the user. For example, in response to checkbox selections, the method can obtain (read) some form of electronically storable data relating to the entity based on which of the machine readable selection items the user checked. Alternatively, in response to other checkbox selections, the method can ignore the user added markings on the machine readable selection items. In addition, in response to the checkmarks, the system can maintain only an image of the user added handwritten text.

Abstract: The present invention discloses a halftone processing of image and text auto detection, which is used to keep both the bit depth of images and the clarity of text when faxing or copying documents. The process of the present invention is stated as follows: choose the background color from the master copy, separate the content of the master copy into images and text with the chosen background color as the criterion, process the images with halftone processing, process the text with line art processing, and then output the processed images and processed text as a whole.

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: Disclosed is an apparatus and method for detecting a face from an image. The apparatus and method uses color components and enables a Support Vector Machine (SVM) having superior recognition performance to previously learn face and non-face images and determine whether an image is a face image based on a learned image database by reducing the size of a feature vector of a face as compared to conventional systems. Accordingly, the apparatus converts a face image into a mosaic image having a minimum size to reduce the dimension of the feature vector, in order to rapidly and correctly detect a face image.

Abstract: There is described a system and method for automatically discriminating between different types of data with an image reader. In brief overview of one embodiment, the automatic discrimination feature of the present image reader allows a human operator to aim a hand-held image reader at a target that can contain a dataform and actuate the image reader. An autodiscrimination module in the image reader in one embodiment analyzes image data representative of the target and determines a type of data represented in the image data.

Abstract: An information processing apparatus includes: a color extraction unit that inputs an additional write document provided by writing additional write information to an original document in different colors and acquires color information on the additional write document; a color analysis unit that analyzes the correspondence between one of a color combination and color space generated by color mixture and the colors extracted based on the colors extracted; a joining and integrating unit that determines overlap between different colors on the additional write document based on the analysis result of the color analysis unit, and that joins the break of the additional write information corresponding to the correspondence portion between the overlap and the break of the additional write information; a determination unit that determines a specification area of the additional write document according to the additional write information joined; and an information analysis unit that reads information contained in the sp

Abstract: An image processing apparatus includes a document input unit that inputs document data of a document, a first identifying unit that identifies a position of a string included in the document, a second identifying unit that identifies a range of a mark given in the document based on an orientation of the string, and a string extracting unit that extracts a string subject to the mark, based on the position of the string identified by the first identifying unit and the range of the mark identified by the second identifying unit.

Abstract: A method for processing image data includes using advantages of both a three-layer MRC model and an N-layer MRC model to create a new 3+N layer MRC model and to generate a 3+N layer MRC image. The method includes providing input image data; segmenting the input image data to generate: (i) a background layer representing the background and the pictorial attributes of the image data, (ii) one or more binary foreground layers, (iii) a selector layer, and (iv) a contone foreground layer representing the foreground attributes of the image data on the background layer; and integrating the background layer, the selector layer, the contone foreground layer, and the one or more binary foreground layers into a data structure having machine-readable information for storage in a memory device. Each binary foreground layer includes one or more pixel clusters representing text pixels of a particular color in the input image data.