Abstract: An apparatus, method, system, computer program and product, each capable of applying document layout analysis to a document image with control of a non-character area. A non-character area is extracted from a document image to be processed. A character image is generated from the document image by removing the non-character area from the document image. The character image is segmented into a plurality of sections to generate a segmented image. The segmented image is adjusted using a selected component of the non-character image to generate an adjusted segmented image. A segmentation result is output, which is generated based on the adjusted segmented image.

Abstract: A system can include a system processor that is programmed or adapted to classify pixels in a document image, and in some instances, to enhance the document image based upon such classification. Image data including pixels is received. For each pixel in some subset of the image data, a feature vector is generated. Each pixel in the subset is classified as text or image based upon its associated feature vector. The classifications can be outputted for storage and/or further processing. Further processing can include pixel level enhancement processing. Such enhancement processing can include application of a sharpening filter to pixels classified as text and of a smoothing filter to pixels classified as image. In some instances, background suppression can be performed upon a subset of the image data prior to classification.

Abstract: A global tag for an image is received identifies one or more objects in the image, and a region-specific tag for the image identifies one or more objects in a region of the image. The global tag and the region-specific tag are stored with the image. Displayed, along with the image, is an identifier for each of the one or more objects identified in the global tag, and an identifier for each of the one or more objects identified in the region-specific tag. Different users are able to maintain different names for the same person, allowing the same tag of the image to be used as the basis for displaying the image with different names for the different users. Additionally, the tags can be used as a basis for generating a credits list of people that are included in a compilation of images.

Abstract: An image to be shared with other users based on input from a first user is received. A second user is identified from a tag of the image, and information is provided, based at least in part on the tag, to one or both of the first user and the second user. Additionally, after editing of an image a determination can be made as to whether a region of the image having an associated tag has been affected by the editing. The tag associated with the region is altered if the region has been affected by the editing, otherwise the tag associated with the region is left unaltered. Furthermore, the tag can include a first portion storing data identifying a region of the image to which the tag corresponds, and a second portion storing data identifying a person shown in the region.

Abstract: An information processing methodology gives rise to an application program interface which includes an automated digitizing unit, such as a scanner, which inputs information from a diversity of hard copy documents and stores information from the hard copy documents into a memory as stored document information. Portions of the stored document information are selected in accordance with content instructions which designate portions of the stored document information required by a particular application program. The selected stored document information is then placed into the transmission format required by a particular application program in accordance with transmission format instructions. After the information has been transmission formatted, the information is transmitted to the application program. In one operational mode, the interface interactively prompts the user to identify, on a display, portions of the hard copy documents containing information used in application programs or for storage.

Abstract: In preparation for rendering respective portions of a document via a respective plurality of engines, objects within the document are identified and characterized. A determination is made as to whether gamut variations between the engines might result in objectionable variations in the appearance of rendered versions of identified objects having similar characteristics. For those objects within the document for which the determination is made that variations might be objectionable, a target gamut is selected to be an intersection gamut of the engines to be used to render the document. For those objects within the document for which the determination is made that variations would be unobjectionable, the target gamut is selected to be that of selected individual engines. A system for selecting target gamuts for objects within a document can include an object identifier, a characteristic identifier and a gamut selector.

Abstract: Aspects of the present invention are related to systems and methods for connected-component labeling.

Abstract: Image editing tools are commonly used to assist with manipulating and saving visual compositions. Many image editing tools provide slicing functionality to create images slices (sub-images) of the visual composition. As provided herein, a slice representation of a visual composition is defined by an arbitrarily chosen set of coordinates within the visual composition. This slice region may be defined independent of other slice regions (e.g. the slice region may or may not overlap, abut, etc. other slice regions). The slice representation comprises the slice region and one or more objects or portions thereof within the slice region. Slice representations may also comprise overlapping objects and/or slice region coordinates. Objects may be manipulated within a slice representation without affecting that object within other slice representations.

Abstract: A JPEG2000 file includes a plurality of boxes containing data suitable to render an image including a metadata box that includes information within the box describing the content of the image. The information within the metadata box describing content may be MPEG-7 data, which is compliant with the MPEG-7 specification.

Abstract: A method of identifying redundant text fragments, which create artificial artifacts only, in an electronic page description language document includes a) providing a page having a plurality of text fragments, each text fragment comprising at least one glyph, the document including Unicode values for all glyphs and geometric information of all text fragments on the page and page description language parameters of all glyphs, b) identifying two text fragments as redundant candidates, if the Unicode sequence of the text fragments have identical corresponding Unicode sequences, c) defining a bounding box of quadrangular shape for each of the two redundant candidates according to their font characteristics, d) calculating the overlapping area of the two bounding boxes, and e) determining whether the two candidates form redundant text fragments by comparing the ratio of the overlapping area to the area of the smaller bounding box of both text fragments with a predetermined threshold.

Abstract: An apparatus and method for processing image data generates image data from a scan of an original image, and creates segmentation data from the generated image data. The segmentation data includes information regarding image types present in the image data corresponding to the scanned original image. Each of the image data and the segmentation data is stored in a storage medium along with a link between the image data and the segmentation data.

Abstract: Image recognition is utilized to facilitate in scoring parse trees for two-dimensional recognition tasks. Trees and subtrees are rendered as images and then utilized to determine parsing scores. Other instances of the subject invention can incorporate additional features such as stroke curvature and/or nearby white space as rendered images as well. Geometric constraints can also be employed to increase performance of a parsing process, substantially improving parsing speed, some even resolvable in polynomial time. Additional performance enhancements can be achieved in yet other instances of the subject invention by employing constellations of integral images and/or integral images of document features.

Abstract: A computer-implemented assigns attributes to an image by processing pixels of the image containing a single marked area spanning more than a single pixel that defines for a current iteration a target attribute so as to determine an optimal function that defines a respective attribute of pixels in the image. Respective attributes are assigned to pixels in the image according to the optimal function; and the attributes of the pixels are displayed.

Abstract: An information display apparatus includes: an extracting unit that extracts a part of an image of a character sequence virtually arranged in a line, as a display area; a display unit that displays the part of the image of the character sequence within the extracted display area; a moving unit that moves the display area on the image of the character sequence; and a designating unit that designates a moving speed of the display area based on at least one of contents of an operation performed by a user and contents of the moving speed designated in past.

Abstract: A document layout analysis program capable of extracting an appropriate set of text blocks from a given document image even in the case where the document layout is so complicated that conventional extraction methods with a single extraction condition would not work well. A plurality of different extraction conditions are stored in an extraction condition memory for use in extracting text blocks from a given document image. In accordance with those extraction conditions, a text block extractor extracts a plurality of sets of text blocks from the document image. A text block consolidator produces a consolidated set of text blocks by performing character recognition on each extracted text block, evaluating validity of each text block based on a result of the character recognition, and selecting most valid text blocks from among the plurality of sets of text blocks.

Abstract: Methods and systems detect objects of interest in a spatio-temporal signal. According to one embodiment, a system processes a digital spatio-temporal input signal containing zero or more foreground objects of interest superimposed on a background. The system comprises a foreground/background separation module, a foreground object grouping module, an object classification module, and a feedback connection. The foreground/background separation module receives the spatio-temporal input signal as an input and, according to one or more adaptable parameters, produces as outputs foreground/background labels designating elements of the spatio-temporal input signal as either foreground or background. The foreground object grouping module is connected to the foreground/background separation module and identifies groups of selected foreground-labeled elements as foreground objects.

Abstract: An image recognition apparatus, method and program capable of discriminatively recognizing an object at an enhanced recognition rate despite an increase in the total number of reference images registered in image databases. When any individual person or public corporation for example is to be specified from the object image obtained by shooting the person or the like, one image database of the attribute corresponding to various situations, or familiarity to the object image is selected automatically, and then the person or corporation is specified from the shot image while referring to the reference images stored in the image database of the selected attribute.

Abstract: Disclosed is an image processing apparatus in which vector data from which noise has been removed and amount of data reduced can be generated in ideal fashion with regard to an illustration area selected from a document image. The document image is input to the apparatus and is segmented into a plurality of areas. A clip-art image is selected from these areas and a plurality of clusters are generated with regard to this image area. When a small area included in the plurality of clusters is determined as a noise, the noise is eliminated by combining the small area with a adjacent cluster. After noise is removed, the cluster group eventually obtained is converted to vector data.

Abstract: A translation device analyses image data that includes characters, to separate and extract a character region, and another region whose structural elements differ from those of the character region; recognizes characters in the region determined to be the character region; extracts a character string related to the other region, from a result of the character recognition, to associate the character string with the character region from which the character string is extracted and the other region; translates the resulting recognized characters; and, based on the association between the character string and the other character region, pastes the resulting translation that includes the character string onto the same page as the other region that is associated with the character string.

Abstract: An information processing methodology gives rise to an application program interface which includes an automated digitizing unit, such as a scanner, which inputs information from a diversity of hard copy documents and stores information from the hard copy documents into a memory as stored document information. Portions of the stored document information are selected in accordance with content instructions which designate portions of the stored document information required by a particular application program. The selected stored document information is then placed into the transmission format required by a particular application program in accordance with transmission format instructions. After the information has been transmission formatted, the information is transmitted to the application program. In one operational mode, the interface interactively prompts the user to identify, on a display, portions of the hard copy documents containing information used in application programs or for storage.

Abstract: A method of segmenting an object in a digital image comprising providing a digital image comprising a plurality of intensities corresponding to a domain of points in a N-dimensional space, selecting a region of interest in the image, determining a threshold intensity value for points in said region of interest, wherein an object of interest is defined by points with an intensity above a first pre-determined threshold, computing a distance map for each point in said object of interest, tobogganing each point in said object of interest based on said distance map, and selecting a cluster based on the results of said tobogganing.

Abstract: One embodiment of the present invention provides a system that efficiently performs a belief-propagation (BP) operation. During this process, for each node i in a BP graph, the system iteratively performs the following operations. First, the system receives incoming messages mji at node i for all adjacent nodes j. Next, the system calculates the full product Pi of all incoming messages mji. The system then produces an outgoing message mij from node i to node j by, computing a partial product Pij of all incoming messages to node i except for the message from node j by dividing the Pi by the incoming message from node j. The system then combines Pij with a data function for node i and a smoothness function between node i and node j to produce outgoing message mij. Finally the system communicates outgoing message mij to node j.

Abstract: One embodiment of the present invention provides a system that facilitates detecting white space tables within a document, wherein a white space table is comprised of text arranged in rows and columns, wherein at least some of the rows and columns are separated by bands of white space rather than by lines. The system operates by identifying an area that includes consecutive lines of text objects with an amount of white space between text objects greater than a specified value. Note that a text object is a string of text without an amount of white space greater than the specified value. The system then determines if the text objects on consecutive lines have widths that are within a specified tolerance of each other. If so, the system checks the spaces between the consecutive lines of text objects to determine if they belong to a single white space table or multiple white space tables.

Abstract: A method for determining an optimal labeling of pixels in computer vision includes modeling an image by a graph having interior nodes and edges where each image point p is associated with a graph node, each pair of nearest neighbor points p, q is connected by a graph edge, each graph node p is associated with a singleton potential c(p), and each graph edge is associated with a pairwise potential function d(p,q). A label is randomly assigned to each point to initialize unary variables including an indicator function that indicates which label is assigned to which point and dual variables including height variables associated with each node p and label a, and balance variables associated with each edge (p,q) and label a. For each label, a new label c is selected, a capacitated graph is constructed and solved. The label selection divides the image into disjoint regions.

Abstract: Techniques for specifying an observing or working position of a sample are provided. Digitized data of a sample is obtained and stored in a 1st storage device. A 1st display area displays an image of a portion containing a desired observing or working position of the digitized data stored in the 1st storage device. A 1st position that is indicated by a pointing device on the 1st display area is stored in a 2nd storage device. The sample is moved to an observing or working position for observation, and an observation image of the sample is stored in the 3rd storage device. A 2nd display area displays the observation image of the sample stored in the 3rd storage device. A position indicated on the 2nd display area and corresponding to the 1st position stored in the 2nd storage device is stored in a 4th storage device.

Abstract: Methods, machines, and computer-readable media storing machine-readable instructions for segmenting pixels in an image are described. In one aspect, a region of background pixels is identified in the image. At least some of the background pixels in the region are located on a boundary spatially delimiting the region. One or more orientation-dependent adaptive thresholds are determined for one or more respective candidate growth directions from a given background pixel located on the region boundary. Color distances between the given background pixel and candidate pixels in a neighborhood of the given background pixel are determined. The region is grown based on application of the one or more orientation-dependent adaptive thresholds to the determined color distances.

Abstract: Disclosed is a medical image processing system comprising a medical image storage server for storing digital image data provided by means such as computerized tomography or magnetic resonance image apparatus in a medical image database; and an image processing system which is coupled to said medical image storage server and to several client computers by TCP/IP protocol; wherein said image processing system comprises a user interface unit which converts the user's command into an electric signal and outputs said electric signal; an image processor unit which reads a medical image out of said medical image database, performs an image processing program comprising a medical image controlling algorithm and outputs a result signal; and an output interface unit which receives said result signal and converts said result signal into a format which can be recognized by a user.

Abstract: An image recognition apparatus, method and program capable of discriminatively recognizing an object at an enhanced recognition rate despite an increase in the total number of reference images registered in image databases. When any individual person or public corporation for example is to be specified from the object image obtained by shooting the person or the like, one image database of the attribute corresponding to various situations, or familiarity to the object image is selected automatically, and then the person or corporation is specified from the shot image while referring to the reference images stored in the image database of the selected attribute.

Abstract: A method and system to convert an image described in a page description language to a contone image. The contone image is halftoned and encoded to generate image data including edge tag data and image data. A tagged state value of each pixel of image data within a predefined neighborhood of pixels is determined. The image data is filtered using a predetermined set of filter weighting values wherein each pixel of image data within the predefined neighborhood of pixels has an associated filter weighting value. A predetermined filtered image value is assigned to each pixel having a tagged state indicating an edge pixel. A summation of all filtered image values for the predefined neighborhood of pixels is assigned when the tagged state of the pixel is a non-edge pixel.

Abstract: Techniques for assigning a region attribute to a region in a drawing are disclosed. One technique includes editing the drawing to define a current region, associating the current region with a previous region having a previous region attribute, and assigning the previous region attribute to the current region. Another technique includes deriving a previous path attribute and a relation for a previous path, editing the drawing to define a current set of paths having current regions, and assigning the previous path attribute to at least one current region based on the relation of the previous path.

Abstract: Embodiments disclosed include methods and systems for reusing labels for connected component labeling including assigning one or more labels to one or more groups of raw data representing one or more regions by designating one or more data structures as containing information about the one or more regions; connecting the one or more labels determined to be related; choosing a root label for the connected one or more labels, the root label determined by locating an earliest data element from the one or more groups of raw data; altering a label list of the one or more labels, the label list altered by flagging the root label to include a region label index; and overwriting one or more region label indexes according to the root label.

Abstract: Embodiments disclosed include methods and systems for assigning one or more labels to one or more segments of data received in an incoming segment to a line buffer for propagated component labeling, including preventing repeated labels in each line of the line buffer by assigning a different label for each of the one or more segments of data received in each line; labeling the incoming segment of the one or more segments of data by adopting a label of an overlapping segment on a prior received line when the overlapping segment does not overlap any other segment of data; labeling the incoming segment of the one or more segments of data by adopting a label of an overlapping segment on a prior received line when the overlapping segment overlaps more than one segment on the incoming segment when the segment is a first segment in the line buffer; and labeling the incoming segment of the one or more segments of data by adopting a label of a last overlapping segment when more than one segment overlaps the incoming s

Abstract: Embodiments disclosed include methods for connected component labeling including labeling groups of raw data as one or more regions, the labeling including designating one or more data structures as containing information about the one or more regions; designating one or more of the regions as one or more subregions to expose a spatial distribution of one or more region features; and arranging at least one memory array with a 1:1 correspondence to a data array associated with the raw data to enable one or more data structures to include feature labels of the one or more subregions, the 1:1 correspondence enabling acquisition of the one or more region features with a controllable precision.

Abstract: Embodiments disclosed include methods and systems for encoding one or more region features in connected components labeling including associating one or more labels for an object with a memory structure, the memory structure including the one or more region features; storing the one or more region features in the memory structure, the one or more region features processed in raster order to provide a correspondence between one or more region properties and an original location of the object; enabling the memory structure to receive one or more extents of the one or more region properties at an adjustable precision and with an adjustable data rate, the adjustable precision and the adjustable data rate determined as a function of an amount of detail to be stored; and enabling the memory structure to receive one or more extents at an adjustable data rate determined as a function of an amount of detail to be stored independent of pixel data.

Abstract: An information storage medium including graphic data and presentation information, and an apparatus and method of processing the graphic data are provided. The information storage medium includes the graphic data, page composition information which defines page composition of the graphic data, and the presentation information indicating when graphic screen data, which is composed with reference to the page composition information of the graphic data, is output to a display screen. Therefore, a graphic object is reusable in graphic data processing, and accordingly, a time taken to process the graphic data is reducible and memory area may be saved.

Abstract: A method of identifying an object in a digital image includes finding a point in a digital image that is a concentration location, initializing a cluster with said concentration location, adding the neighboring points of the concentration location to a list, selecting a neighbor point with an extremal potential value from said list, determining a slide direction of all neighbors of said selected point and identifying those neighbors that slide to the selected point, adding those neighbor points not already in the list to the list, adding the selected point to the cluster, and repeating the steps of selecting a neighbor point with an extremal potential value, determining a slide direction, adding points to the list, and adding the selected point to the cluster, until the list is empty.

Abstract: A system for learning an attention model for an image based on user navigation actions while viewing the image is provided. An attention model learning system generates an initial attention model based on static features derived from the image. The learning system logs the actions of users as they view the image. The learning system identifies from the actions of the users those areas of the image that may be of user interest: After the learning system identifies areas that may be of user interest, the learning system attempts to identify attention objects based on those identified areas. After identifying the user attention objects, the learning system updates the attention model for the image to reflect the additional information provided by the user attention objects.

Abstract: A method for automatic centerline extraction for a virtual endoscopy image of an organ having a boundary surface includes centering on selected points of an initial path through the image, which is derived from an endoscopy dataset, respective spheres exhibiting respective maximal diameters short of contacting the boundary surface; and forming a centered path consecutively joining centers of the spheres.

Abstract: A business form processing program to cause a computer to execute a character box-image reading step for reading by a scanner all colors of a business form with blank character boxes and storing them as character box images, a business form reading step for reading by a scanner a recognized image from which colors of unwanted recognized parts on a filled-out business form are dropped out and storing it, a character recognizing step for recognizing characters on the recognized image, and a composite display step for displaying the character recognized results and a filled-out business form image in which the recognized image is superposed on the character box image when character recognized results need correted.

Abstract: This present invention provides an image processing system and image processing method which can reliably transmit image information to a destination without attaching a large file which applies load to an e-mail system or reception terminal and make the receiving side easily acquire necessary image data on the basis of determination on the receiving side. In an image input/output device (10), image information is input from an image input device (201) and stored in a HDD (208) in a control unit (200). A low-resolution image or vector data is generated from the image information in accordance with the properties of objects contained in the image information. The generated information and information about the storage location of the image information are transmitted to a designated transmission destination.

Abstract: An image processing apparatus includes a segment length measuring unit, a segment specifying unit and an information embedding unit. The segment length measuring unit measures lengths of line segments in a pixel block contained in an image by scanning the pixel block. The segment specifying unit specifies a line segment in which information is to be embedded, based on a measurement result of the segment length measuring unit. The information embedding unit embeds the information by changing the length of the line segment specified by the segment specifying unit based on the information to be embedded.

Abstract: Vector data corresponding to a scanned original image is generated. An edit image of the original image corresponding to the display resolution of a display is generated on the basis of the vector data, and display of the edit image on the display is controlled.

Abstract: The system and method facilitate the control and management of information and actions related to the computerized scanning, categorization, processing, storage, and retrieval of paper documents and electronic document images for the purposes of creating electronic data; data entry; data capture; data classification and categorization; and document-, file-, and records-management. The systems and methods facilitate the conversion of paper documents into electronic images and into more useful forms.

Abstract: An image forming apparatus that processes image data using plural processors that operate in parallel includes an image-data receiving section that receives inputted image data, a layout analyzing section that analyzes a layout structure including a predetermined area on the basis of the image data received by the image-data receiving section, a processing-amount calculating section that calculates a processing amount for the predetermined area in the layout structure of the image data analyzed by the layout analyzing section, and a processing-processor determining section that allocates, in processing for all areas in the layout structure analyzed by the layout analyzing section, processing for the predetermined areas to any one of the plural processors on the basis of the processing amount calculated by the processing-amount calculating section.

Abstract: A system creates an electronic version of a document from page-images of the document, wherein the electronic version replicates both the logical content and the physical appearance of the original document. During operation, the system receives the page-images for the document. Next, the system extracts character images from the page-images, and generates a synthetic font for the document from the extracted character images. Finally, the system constructs the electronic version of the document by, using the synthetic font to represent text regions of the document, and by using image-segments extracted from the pages-images to represent non-text regions of the document.

Abstract: In one embodiment, the invention provides a method for determining a logical structure of a document. The method comprises generating at least one document hypothesis for the whole document; for each document hypothesis, verifying said document hypothesis including (a) generating at least one block hypothesis for each block in the document based on the document hypothesis; and (b) selecting a best block hypothesis for each block; selecting as a best document hypothesis the document hypothesis that has the best degree of correspondence with the selected best block hypotheses for the document; and forming the document based on the best document hypothesis.

Abstract: An image processing apparatus includes a plurality of processor elements including registers and configured to process respective data items, a global processor configured to control the plurality oaf processor elements; the global processor and the plurality of processor elements constituting an SIMD microprocessor, and a data control device coupled to a data transfer port for accessing the registers, the processor elements configured to perform a contiguity check and tentative labeling of pixels adjacent in a sub-scan direction as parallel processes with respect to binary image data, the data control device configured to perform a contiguity check and tentative labeling of pixels adjacent in a main scan direction as consecutive processes, and the parallel processes performed ahead of the consecutive processes with respect to a line of interest in the binary image data.

Abstract: A method and computer program product for reflowing a PDL page without using the original application used to create the PDL page. The method and computer program product include receiving a page represented in a page description language, the page including a plurality of page objects, and changing one or both of a size of the page and a size of one or more of the page objects, while maintaining spatial relationships between the page objects.

Abstract: A method of labeling pixels in an image is described where the pixel label is selected from a set of three or more labels. The pixel labeling problem is reduced to a sequence of binary optimizations by representing the label value for each pixel as a binary word and then optimizing the value of each bit within the word, starting with the most significant bit. Data which has been learned from one or more training images is used in the optimization to provide information about the less significant bits within the word.

Abstract: The present invention relates to method, apparatus and storage medium for enhancing document image, and method, apparatus and storage medium for character recognition. For enhancing the document image especially half-tone block image and improving the recognition ratio thereof, the block image is segmented into line images, which are subject to noise reduction. Then, based on the connected component densities, the noise-reduced line images are sorted into three types including normal line image, broken-stroke line image and hollow-stroke line image. Based on their types and other properties, the noise-reduced line images are enhanced, generating enhanced line images, which as a whole constitutes an enhanced block image.