Abstract: Image processing apparatus and methods perform effective labeling of objects in an image while advantageously requiring only a small memory. The apparatus and methods practicably and effectively implement various applications, in particular, a detection technique for determination of a detection target. The apparatus comprises a detection unit for detecting values of pixels adjacent to a target pixel within a transformation matrix area of a binary image. The apparatus also includes a labeling unit for assigning a label value to the target pixel. The assigned label value is either a new value or the value existing in the pixels adjacent the target pixel, depending on the value of the adjacent pixels' label.

Abstract: A method for increasing efficiency of interaction by an operator with data on a computer display includes presenting the data to the operator on the computer display, and providing multiple instances of an on-screen control at different locations on the display for selection by the operator using a pointing device linked to the display. The control is actuated responsive to the selection by the operator of any of the instances of the control on the display.

Abstract: Disclosed are embodiments of systems and methods for segmenting an image into at least two layers, a foreground and a background layer. An embodiment of the present invention includes 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. In embodiments, additional processes may be performed on the image including, but not limited to, filtering, image enhancing, shape refining, image compression, etc.

Abstract: Methods and apparatus for effectively identifying the occlusion of objects, such as persons, having a high degree of freedom. In an example embodiment, after initialization, an image is input, and an image region is extracted from image data. The distance is employed that is obtained when the shape of a two-dimensional histogram in the color space is transformed into the feature space. A graph is formed by using the regions between the frames. A confidence factor is provided and image features are provided as weights to the edges that connect the nodes. Processing is performed and the confidence factor is examined. A connection judged less possible to be a path is removed. When there is only one available connection for the occlusion point, this connection is selected.

Abstract: One embodiment of the present invention provides a system that removes noise from an image. During operation, the system first identifies blobs in the image, wherein a blob is a set of contiguous pixels which possibly represents a character or a portion of a character in the image. Next, the system analyzes the blobs to dynamically determine a “noise threshold” for the blobs. The system then removes blobs from the image which are below the noise threshold.

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: An artifact removal and quality assurance method and system for digital images, wherein a document comprising at least one printed page is scanned or the original image data are otherwise input. The input digital image data are segmented into components as to content type. The components are classified as either information or noise components. An information component image defined by the information components and a noise component image defined by the noise components are generated and displayed to the user. The user inputs quality assurance input data to indicate zero or more improperly classified components and any improperly classified component is reclassified. The component images are then regenerated and displayed to account for the reclassified component(s). The reclassified component is moved as a unit in real time as viewed by the user from an original location in one of the component images to a corresponding location in the other of the component images.

Abstract: Exemplary embodiments of the present invention provide a system to generate visual-guidance information in which the system can be reduced in size and cost and which ensures a proper eye flow. A layout unit operates in such a way that a layout image is segmented into multiple regions; the saliency features and positional information of the partial regions are calculated from image data, and the calculated saliency features are weighted. A starting-point region is then detected from among the multiple partial regions from the calculated saliency features and the reference points of the partial regions are detected from a visual-guidance feature space based on the weighted saliency features and the calculated positional information. Then the distance between the detected reference points is calculated and visual-guidance information is generated from the calculated inter-reference-point distance.

Abstract: A computer-implemented method is provided for converting a scanned-in electronic image into a token-based file. The method includes generally five steps. First, various tokens (i.e., graphical units) are identified in the electronic image. Second, the identified tokens having similar shapes are classified together to form a token group, to thereby form multiple token groups, each including one or more tokens having similar shapes. Third, in each token group, a representative token is found, which morphologically represents the shapes of tokens included in the group. Fourth, each representative token is converted into a vectorized token, which is a mathematical representation of the shape of the representative token. Fifth, each of the vectorized tokens is associated with the positions of the tokens in the electronic image represented by the vectorized token. Thus, upon rendering, the vectorized token is displayed to thereby create a page image consisting only of clean images of vectorized tokens.

Abstract: A system and method for multi-label image segmentation is provided. The method comprises the steps of: receiving image data including a set of labeled image elements; mapping a change in intensities of the image data to edge weights; determining potentials for each image element in the image data; and assigning a label, based upon the determined potentials, to each image element in the image data.

Abstract: A method of processing an image reduces the number of pixels constituting the image by sequentially eliminating alternate rows and columns of pixels, the information represented by each pixel being eliminated (a “source” pixel) being redistributed into adjacent “destination” pixel locations. The redistribution is made in proportion to the similarity between the source and each destination pixel, e.g., similarity of color and/or luminance values.

Abstract: An apparatus and software for processing an image reduces the number of pixels constituting the image by sequentially eliminating alternate rows and columns of pixels, the information represented by each pixel being eliminated (a “source” pixel) being redistributed into adjacent “destination” pixel locations. The redistribution is made in proportion to the similarity between the source and each destination pixel, e.g., similarity of color and/or luminance values.

Abstract: According to an embodiment of the invention, a method and apparatus for image segmentation are described. An embodiment of a method comprises inserting a state comprising a set of image segmentations into a queue, the queue being ordered by priority, the set of image segmentations having a priority representing a bound for a quality of the segmentations; extracting the state in the queue having the highest priority; if the extracted state is a terminal state, halting and outputting the extracted state as a solution; if the extracted state is not a terminal state refining the extracted state into a plurality of sets of segmentations, each of the plurality of sets having a priority, inserting the plurality of sets of segmentations into the queue, and iteratively repeating the extraction of the state in the queue having the highest priority.

Abstract: A method of segmenting an image includes representing an image by a grid with a plurality of nodes, terminals, and edges, the terminals including a source and a sink. The edges include n-links and t-links, where each n-link connects a pair of nodes, and the t-links connect a node to a terminal, and each t-link and n-link has an associated cost. The method includes initializing a node height table, a flow excess table, a t-link capacity table, and an n-link capacity table based on the t-link and n-link costs, and updating the node height table, the flow excess table, the t-link capacity table, the said n-link capacity table in parallel for all nodes until the flow excess table is zero for all nodes. The method steps are performed in parallel for all nodes on a graphics processing unit.

Abstract: A system and method for labeling feature clusters in frames of image data for optical navigation uses distances between feature clusters in a current frame of image data and feature clusters in a previous frame of image data to label the feature clusters in the current frame of image data using identifiers associated with the feature cluster in the previous frame of image data that have been correlated with the feature clusters in the current frame of image data.

Abstract: A data capture and mining method which enables identification of characters and words through their visible patterns. Specifically, a data capture and mining method involves searching a scanned image using isomorphic, graphical pattern matching techniques that eliminate both the need to convert imaged writing to electronic format through, e.g., OCR and the subsequent need to convert the electronic text into English.

Abstract: An image processing apparatus includes: a reading unit adapted to read an image and to generate image data representing the image; a separating unit adapted to separate the image data obtained by the reading unit into a plurality of objects corresponding to attributes; a selecting unit adapted to select a predetermined attribute of the image; a vectorization unit adapted to perform a vector conversion process for the image data separated by the separating unit in accordance with the predetermined attribute selected by the selecting unit; and an output unit adapted to output the image data processed by the vectorization unit.

Abstract: A print controller for making a print device print in such a manner that a grouping for each record included in printed matter can be easily recognized is provided. A print control program stored on computer readable storage media for outputting a business form by sending output form data to a print device includes the steps of inputting form data which indicates a layout of the business form; inputting variable length field data consisting of a plurality of records; setting a print condition for each record included in the input field data; generating output form data of the business form by overlaying the field data set with the print condition on the input form data; and outputting the business form by sending the generated output form data to the print device.

Abstract: An imaging technique permits selective flattening of objects within page description files. The selective aspect of the flattening may pertain to the selection of particular objects to be flattened, selection of the degree of flattening to be applied to objects, or both. In some embodiments, selective flattening of objects in a page description file may be permitted based on an assessment of color correction efficacy. For example, the degree of flattening may be iteratively adjusted to achieve acceptable color correction results. Alternatively a user may be notified in the event acceptable color correction results have not been achieved. A color error between bitmap files generated from a color corrected, unflattened page description file and from a color corrected, flattened page description file may be measured. When the measured error between the two bitmaps exceeds a predetermined value, an amount of file flattening may be adjusted to reduce the measured error.

Abstract: An algorithm for estimating which pixels belong to the background of a scanned page. The algorithm is particularly designed to handle situations in which the page background varies in color/intensity, as is case when bleed-through artifacts from the reverse side of the page appear in the background. In determining background regions, including properly classifying bleed-through artifacts regions as such, the algorithm uses multiple local and global criteria for making the determination. In addition to being able to find large connected pieces of background, the algorithm is also able to find isolated islands of background by analyzing transition characteristics of neighboring regions. Regions are identified on the basis of similar local features and also by the nature of transitions between foreground regions that do not directly share a boundary. An adaptive white-point adjustment technique based on identified background regions improves the perceived quality of the printed output.

Abstract: The invention relates to a method for providing rendered images based on image segmentation with determining an edge within the image introduced by boundaries of image segments. To allow shift-based rendering, the invention provides determining an edge within the image introduced by boundaries of image segments, determining an edge region around the edge, determining a first displacement field for the segments, determining a second displacement field for the edge region, merging the first and the second displacement field into a third displacement field having a displacement of the first displacement field for the segments and a displacement of the second displacement field for the edge region, such that the edge region is treated as a separate object with a separate displacement, and shifting the image pixels according to the third displacement field.

Abstract: In a boundary active only scheme proposed by the present invention, only a cell in a boundary of region growth is brought into an active mode, and the other cells are brought into a standby mode. The respective cells perform state transition in parallel, and decision of the state transition performed for each clock cycle is not performed in a case where any of the three conditions that none of the adjacent cells is ignited, the cell itself is already ignited, and the cell already belongs to a certain divided region is satisfied. Therefore the number of simultaneously operating cells and that of coupling weight registers are minimized, and control is automatically executed to reduce power consumption.

Abstract: A method for image separating, said method being applied to an electronic apparatus to separate a foreground and a background of an image displayed on said apparatus, comprising the steps of scanning pixels in said image, applying arithmetic algorithm on said pixels and forming a plurality of segments on said image by defining pixels adjacent to each other and similar in color as one segment; examining foreground label and background label marked by an user; merging segments labeled by said foreground label into a foreground region and segments labeled by said background label into a background region, and applying arithmetic algorithm on an unlabeled segment to merge with an adjacent segment, foreground region or background region having the least difference in color; repeating said merging step until all segments are merged into a foreground region or a background region, thereby separating said image into a foreground region and a background region.

Abstract: A method processes an input image securely. An input image is acquired in a client and partitioned into a set of overlapping tiles. The set of overlapping tiles is transferred to a server. In the server, motion pixels in each tile that are immediately adjacent to other motions pixels in the tile are labeled locally to generate a set of locally labeled tiles. The set of locally labeled tiles is transferred to the client. In the client, the set of locally labeled tiles is labeled globally to generate a list of pairs of unique global labels. The list of pairs of unique global labels is transferred to the server. In the server, the pairs of unique global labels are classified into equivalence classes. The equivalence classes are transferred to the client and the motion pixels are relabeled in the client according to the equivalence classes to form connected components in the input image.

Abstract: A manual windowing with auto-segmentation assistance method and system are disclosed that include defining manual tags to be assigned to one or more windows via a tag selection module, assigning the defined manual tags to the one or more windows via a manual tag assignment module and auto-segmenting the one or more windows within the display medium by producing auto-segmentation tags via the auto-segmentation module. Furthermore the method and system according to this invention provide for mapping tags to the auto-segmentation tags via a tag mapping module and merging the manual tags and the auto-segmentation tags via a merging module.

Abstract: A position of a three-dimensional (3D) object relative to a display surface of an interactive display system is detected based upon the intensity of infrared (IR) light reflected from the object and received by an IR video camera disposed under the display surface. As the object approaches the display surface, a “hover” connected component is defined by pixels in the image produced by the IR video camera that have an intensity greater than a predefined hover threshold and are immediately adjacent to another pixel also having an intensity greater than the hover threshold. When the object contacts the display surface, a “touch” connected component is defined by pixels in the image having an intensity greater than a touch threshold, which is greater than the hover threshold. Connected components determined for an object at different heights above the surface are associated with a common label if their bounding areas overlap.

Abstract: Certain embodiments of the present invention provide an improved method for automatically labeling an image using an intraoperative imaging system. The method includes acquiring a first image at a first position, labeling the first image with a first label, acquiring a second image at a second position, automatically labeling the second image with a second label based at least in part on the first label, the first position, and the second position.

Abstract: A method and system for visualizing regions in an image is provided. The method comprises computing a regional response around a region in the image, deriving a region score based on from the regional response for the region and labeling the region in the image by comparing the region score to a plurality of probabilistic models.

Abstract: During a training phase we learn parts of images which assist in the object detection and recognition task. A part is a densely represented area of an image of an object to which we assign a unique label. Parts contiguously cover an image of an object to give a part label map for that object. The parts do not necessarily correspond to semantic object parts. During the training phase a classifier is learnt which can be used to estimate belief distributions over parts for each image element of a test image. A conditional random field is used to force a global part labeling which is substantially layout-consistent and a part label map is inferred from this. By recognizing parts we enable object detection and recognition even for partially occluded objects, for multiple-objects of different classes in the same scene, for unstructured and structured objects and allowing for object deformation.

Abstract: Given an image of structured and/or unstructured objects we automatically partition it into semantically meaningful areas each labeled with a specific object class. We use a novel type of feature which we refer to as a shape filter. Shape filters enable us to capture some or all of shape, texture and appearance context information. A shape filter comprises one or more regions of arbitrary shape, size and position within a bounding area of an image, paired with a specified texton. A texton comprises information describing the texture of a patch of surface of an object. In a training process we select a sub-set of possible shape filters and incorporate those into a conditional random field model of object classes. That model is then used for object detection and recognition.

Abstract: A system and method are disclosed for automatically classifying images of pages of a source, such as a book, into classifications such as front cover, copyright page, table of contents, text, index, etc. In one embodiment, three phases are provided in the classification process. During a first phase of the classification process, a first classifier may be used to determine a preliminary classification of a page image based on single-page criteria. During a second phase of the classification process, a second classifier may be used to determine a final classification for the page image based on multiple-page and/or global criteria. During an optional third phase of classification, a verifier may be used to verify the final classification of the page image based on verification criteria. If automatic classification fails, the page image may be passed on to a human operator for manual classification.

Abstract: A computer readable medium embodying instructions executable by a processor to perform a method for seeded image segmentation using l? minimization, the method including providing an image comprising a set of pixels, wherein a foreground seed label is given for at least one pixel of the image and a background seed label is given for at least another pixel of the image, determining an affinity function for every pair of neighbor pixels, solving the l? minimization, which assigns a probability to each pixel, labeling each pixel as foreground pixel or background pixel according to a threshold of the probability, and outputting the image including the segmentation labels.

Abstract: A ruled line extracting apparatus, a ruled line extracting program and a ruled line extracting method re-extract a ruled line by changing the predetermined requirements to be met by ruled line s when a ruled line candidate extracted according to the requirements shows a low reliability.

Abstract: A digitization process and system which involves the use of a novel label, labeling system and labeling methodology. According to the teachings of the present invention, the label is comprised of two parts one of which is transparent and the other of which is opaque. Bates numbers or other identifiers according to some sequential numbering or ordering scheme are placed on the opaque portion of the label. The labels are placed on document edges prior to scanning and removed after scanning. Following scanning, an interactive quality control process is carried out in order to ensure image integrity against the original document sequence and integrity. After the sequence and integrity of the images is verified, the images are cropped so as to remove the ordering information and then the document may be stored possibly for later retrieval via its unique identifier.

Abstract: A method of generating an interactive document is provided having the steps of allocating and recording a document identity in a computer system, associating the document identity with a page description for the document in the computer system, and communicating at least part of the page description and the document identity with a printer networked with the computer system. The page description includes a description of graphical information and coded data of the document. The coded data includes data on the document identity and a plurality of locations of the document. By communicating the page description and document identity to the printer, the printer is able to generate the coded data and print the document.

Abstract: An image matching method and system for use with multiple images of a scene captured from different angles. Image matching is performed by identifying a plurality of segments within at least two images, determining an initial disparity values for pixels in the images and then determining initial disparity planes for the segments by fitting a plane to initial disparity values for the segments. A refined disparity plane set is created by iteratively refitting the disparity planes by using various fitting cost functions and weighted linear systems. A labeling of each segment to a disparity plane is made by minimizing a global energy function that includes energy terms for segment to disparity plane matching as well as penalizing disparity plane discontinuities between adjacent image segments.

Abstract: A cell lineage can be constructed in a less labor intensive manner and in less time by using a computer. Areas, which are misidentified as nuclei, are efficiently removed. The invention comprises the steps of: selecting one or more nuclei for making a forward link from extracted nucleus candidates, in a plurality of 4D microscopic images in which the nucleus candidates are extracted; obtaining forward linkage information by sequentially extracting a nucleus candidate that meets a predetermined link condition with regard to the selected one or more nuclei from said 4D images; selecting one or more nuclei for making a reverse link from the forward linkage information; and obtaining backward linkage information by sequentially extracting a nucleus candidate that meets a predetermined link condition with regard to the selected one or more nuclei for backward link from said 4D images, removing misidentified nucleus candidates from the forward link information based on the reverse link information.

Abstract: A labeling process unit groups a continuous black pixel area as one group in the binary image data read by an image input device, and extracts the group bounding rectangle information about the group. A row extracting process unit extracts row rectangle information from the position information about the extracted group bounding rectangle. An overlap integrating process unit determines the overlap between the group bounding rectangles contained in the extracted row rectangle, and performs an overlap integrating process of integrating overlapping groups into one group. The ratio of the number of group bounding rectangles contained in the row rectangle before performing the overlap integrating process to the number of the group bounding rectangles contained in the row rectangle after performing the overlap integrating process is obtained, and the language of the characters written in the original is determined based on the difference in ratio.

Abstract: Image processing methods, image management systems, and articles of manufacture are described. According to one embodiment, an image processing method includes accessing image data of a plurality of images, defining a plurality of regions in individual ones of the images, wherein the regions individually comprise a plurality of image forming elements having a common characteristic, comparing a region of one of the images with respect to regions of a plurality of others of the images, and providing information indicative of similarities of the one image relative to the others of the images using results of the comparing.

Abstract: A method of separating text and graphs in digital image data is used to separate digital image data into graph data and text data. According to a default separating parameter, the digital image data are partitioned into several operating matrices. One then sets a default crossing reference level for comparison analyses to compare adjacent pixel units in each operating matrix. When the digital characteristic value of a pixel unit is greater than the default crossing reference level and the digital characteristic value of its one adjacent pixel unit are smaller the default crossing reference level, the operating matrix is given a weight. Afterwards, all the weights are added up to give a weighted statistical value, which eventually is used to separate the graph data from the text data.

Abstract: In an image forming apparatus, a control section performs a control to compress/decompress at least one of first image data and second image data by one of a first compression/decompression method and a second compression/decompression method on the basis of the determination of the kind of an original, and to perform one of a first printing operation and a second printing operation.

Abstract: A method for improving mixed raster compression segmentation utilizes a second stage of a process to generate the MRC Selector plane by operating on a multibit selector (GraySel) signal which is produced by a first stage process. The first stage methods used to generated the GraySel can be PDL or scan oriented. The binary Selector signal produced by the second stage minimizes the compression noise evident in the reconstructed image. This second stage processing relies on knowing the size of the JPEG minimum coded unit (MCU) which will be used to compress the segmented Foreground and Background planes. The idea is to move false (soft) edges away from the real (hard) edges by as large a distance as possible up to the point where they fall off the boundary of the MCU block. Thus a soft edge which occurs between two hard edges is either eliminated or repositioned to the midpoint and a soft edge between a hard edge and the MCU boundary is moved to the boundary.

Abstract: A method and system are provided to report the findings of an expert's analysis of image data. The method and system are based on a reporting system that forms the basis of an image management system that can efficiently and systematically generate image reports, facilitate data entry into searchable databases for data mining, and expedite billing and collections for the expert's services. The expert identifies a significant finding on an image and attaches a location:description code to the location of that finding in order to create a significant finding and an entry into a database. Further descriptions of that finding, such as dimensional measurements, may be automatically appended to the finding as secondary attributes. After the evaluation, the system sorts the findings in the database and presents the findings by prioritized categories. The expert edits and approves a multimedia report which may be delivered by electronic means to an end-user.

Abstract: To improve usability by prevent a print output which is not desired by the user from being outputted, for example, whether an image is outputted when a deterioration state exceeds a specific deterioration degree or not is set by an operation panel 1012, and when raster image information which is deteriorated and formed in accordance with inputted print information is printed, the printing is stopped in accordance with the setting.

Abstract: The invention aims at providing personal identification in environments where non-contact is required, with high accuracy even though using a finger vein pattern images unclear and susceptible to positional deviations, wherein it has: a means for acquiring finger vein patterns without contact; a means for carrying out rotational correction using the outline of a finger as a method of taking out a vein pattern contained in the acquired image; a means for normalizing the position of the finger image with reference to the fingertip; a means for acquiring an overall vein pattern statistically by repetitively tracking regions of dark luminance intensities for a desired length from a desired position in the image; a matching means for comparing regions where vein patterns manifest vivid features; and a means for independent matching of subregions and evaluating positional deviations where matching is recognized.

Abstract: A plurality of binary images are obtained from one form image by binarizing the form image by using a plurality of binarizing threshold values for improving a recognition rate of the search form irrespective of a state of the inputted form image, and format data are generated respectively from the plurality of binary images. If the inputted form image is a binary image, after the binary image has been converted into a multi-valued image by a vignetting filter, a plurality of binary images are obtained from one form image by executing the binarizing processing by use of the plurality of binarizing threshold values respectively, thereby generating the format data respectively from the plurality of binary images.

Abstract: Xerox Docket No. D/A0037Q Document authentication is accomplished by acquiring document image data, generating a set of features of the document, and generating an assist channel that includes information on how to generate the set of features. The set of features and the assist channel are digitally signed and then append to the document. Document verification is accomplished by acquiring document image data and verifying the signature. If the signature is valid, a set of features of the document is generated using information contained in the assist channel appended to the document. The generated set of features is then compared to the set of features appended on the document. If the sets do not match, the document is determined to have been altered sometimes after the assist channel was appended to the document, i.e., the document is not genuine. Otherwise, the document can be considered to be genuine.

Abstract: The invention aims at providing personal identification in environments where non-contact is required, with high accuracy even though using a finger vein pattern images unclear and susceptible to positional deviations, wherein it has: a means for acquiring finger vein patterns without contact; a means for carrying out rotational correction using the outline of a finger as a method of taking out a vein pattern contained in the acquired image; a means for normalizing the position of the finger image with reference to the fingertip; a means for acquiring an overall vein pattern statistically by repetitively tracking regions of dark luminance intensities for a desired length from a desired position in the image; a matching means for comparing regions where vein patterns manifest vivid features; and a means for independent matching of subregions and evaluating positional deviations where matching is recognized.

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: Methods and apparatus for effectively identifying the occlusion of objects, such as persons, having a high degree of freedom. In an example embodiment, after initialization, an image is input, and an image region is extracted from image data. The distance is employed that is obtained when the shape of a two-dimensional histogram in the color space is transformed into the feature space. A graph is formed by using the regions between the frames. A confidence factor is provided and image features are provided as weights to the edges that connect the nodes. Processing is performed and the confidence factor is examined. A connection judged less possible to be a path is removed. When there is only one available connection for the occlusion point, this connection is selected.