Abstract: A method for identifying a table image in a document image includes identifying a frame image in the document image, identifying white areas within the frame image, identifying broken lines within the frame image, calculating horizontal and vertical grid lines based on the identified white areas and the identified broken lines, and determining whether the frame is a table image based on the calculated horizontal and vertical grid lines.

Abstract: A method for increasing the accuracy of image data classification in a page analysis system for analyzing image data of a document page. The method includes inputting image data of a document page as pixel data, analyzing the pixel data in order to locate all connected pixels, rectangularizing connected pixel data into blocks, analyzing each of the blocks of pixel data in order to determine the type of image data contained in the block, outputting an attribute corresponding to the type of image data determined in the analyzing step, and performing optical character recognition to attempt to recognize a character of the block of image data in the case that the analyzing step cannot determine the type of image data contained in the block.

Abstract: A system to render a color image using a binarized image representing the color image and a hierarchical tree structure representing the color image, the hierarchical tree structure including nodes representing respective blocks of image data within the color image, the nodes containing color information for respective blocks. The system includes a defining step to define, in a memory, a color image rendering area corresponding to a block of image data in the color image, an obtaining step to obtain foreground color information from a node corresponding to the block of image data, a detecting step to detect black pixel locations in the binarized image within an area of the binarized image corresponding to the block of image data, and an assigning step to assign the foreground color to pixels at locations in the color image rendering area corresponding to the detected black pixel locations.

Abstract: A document image capture method and scanner, and an image processing apparatus incorporating such a scanner, in which a document is scanned two or more times. The first scan preferably provides bi-level image data, which is analyzed to identify blocks of uniform image type (for example, text, line drawing, grayscale image, or full-color image) within the document. The second scan, preferably performed at lower resolution than the first, provides grayscale or color information, which is substituted in the grayscale or color blocks, respectively, for the bi-level information obtained in the first scan. A third scan, to provide information of the third type, may also be performed.

Abstract: A method for identifying a table image in a document image includes identifying a frame image in the document image, identifying white areas within the frame image, identifying broken lines within the frame image, calculating horizontal and vertical grid lines based on the identified white areas and the identified broken lines, and determining whether the frame is a table image based on the calculated horizontal and vertical grid lines.

Abstract: A system to identify features of a color document in which primary color values representing a color document are input, a threshold binarizing range is calculated based on the input values, the input values are binarized into binary values based on the threshold binarizing range, a colored region is identified within the document, and a frame is defined surrounding the identified colored region. A second threshold binarizing range is calculated based on input primary values corresponding to the colored region, and the input primary values corresponding to the colored region are binarized into binarized values based on the second threshold binarizing range.

Abstract: A method for increasing the accuracy of image data classification in a page analysis system for analyzing image data of a document page. The method includes inputting image data of a document page as pixel data, analyzing the pixel data in order to locate all connected pixels, rectangularizing connected pixel data into blocks, analyzing each of the blocks of pixel data in order to determine the type of image data contained in the block, outputting an attribute corresponding to the type of image data determined in the analyzing step, and performing optical character recognition to attempt to recognize a character of the block of image data in the case that the analyzing step cannot determine the type of image data contained in the block.

Abstract: A method for block selection on a image of a table, the table including rows and columns defined by visible and non-visible grid lines and containing table cells, includes identifying super-cells that include one or more table cells, wherein super-cells are identified according to traced white areas surrounding table cells and bounded by visible grid lines, determining whether vertical and horizontal grid lines bounding each table cell are visible or non-visible, and determining whether vertical and horizontal grid lines bounding each super-cell are visible or non-visible.

Abstract: A method for identifying and extracting text data from a table-cell frame. The method includes the steps of tracing connected components of a document image, tracing white contours within a connected component, defining a frame outline based on the white contours, identifying unattached character data inside the frame outline, and defining an initial rectangular area inside the frame outline.

Abstract: A page analysis system, which utilizes a block selection application to analyze image data of a page in a multi-page document, includes the features of 1) returning an error code in the case that data to be stored in either a common memory work area or a hierarchical tree storage memory area exceeds the allocated memory space, 2) calculating a skew angle of a page and returning an error code in the case the skew angle exceeds a predefined maximum skew angle, 3) designating a default processing direction in the case a user fails to input directional information of the image data in the page, 4) determining and indicating whether identified picture image information represents a halftone image, a line drawing, a joint line, or unknown picture type, 5) analyzing image data of a portion of a page which has been designated by input coordinates, and 6) identifying a block which contains at least two image types as a composite block and identifying the type of image data within the composite block.

Abstract: A document image capture method and scanner, and an image processing apparatus incorporating such a scanner, in which a document is scanned two or more times. The first scan preferably provides bi-level image data, which is analyzed to identify blocks of uniform image type (for example, text, line drawing, grayscale image, or full-color image) within the document. The second scan, preferably performed at lower resolution than the first, provides grayscale or color information, which is substituted in the grayscale or color blocks, respectively, for the bi-level information obtained in the first scan. A third scan, to provide information of the third type, may also be performed.

Abstract: A page analysis system which analyzes image data of a document page includes analysis of image data of one of a plurality of portions of the page, identification of a block of image data which has an association to another separate block of image data, and determination of whether or not picture information in the image data is half-tone line-drawing, joint-line, or unknown.

Abstract: Method and apparatus for selecting text and/or non-text blocks in a stored document includes functions and structure for identifying connected pixel components in a stored document, separating the identified pixel components into text and non-text components, searching the document for visible and invisible lines along edges of the non-text components, forming irregularly-shaped text and non-text blocks using the identified text components and the visible and invisible lines, detecting the text orientation for each formed text block, the text orientation including horizontal text orientation and vertical text orientation, extracting text lines from the text block based on the detected orientation, detecting the skew angle for the stored document based on the extracted lines, and modifying the formed text and non-text blocks based on the detected skew angle. The thus-formed text blocks are preferably subjected to character recognition routines.

Abstract: In a feature extraction system for analyzing image data of an input document image, a feature extraction method identifies image data as a table image and identifies text image within the table image by performing the steps of inputting image data of a document page, performing block selection processing on the document page, the block selection process identifies and separates the image data into blocks having the same image type, identifying table image data based on the separated blocks of image data, identifying text blocks within the table image data, horizontally sorting all text blocks located in the table image data based on horizontal position information, vertically sorting all text blocks located in the table image data based on vertical position information, separating text blocks into rows and columns based on a result of the vertical and the horizontal sorting steps, assigning column and row address coordinates to each text block in the table image data based on the separating step, and storing

Abstract: A system for editing the hierarchical tree structure which is created by a block selection system to correspond to a block template which represents a document image, wherein the hierarchical tree structure includes a plurality of nodes, each of which represents a block of document image data in the block template of a document image and contains document feature data defining features of the block of image data. The system operates to download from memory the hierarchical tree structure, generate and display a block template representing a document image corresponding to the hierarchical tree structure in memory, select a block of document image data to be edited in the displayed block template, edit a feature of the selected block of image data and update the document feature data in a node corresponding to the selected block of image data.

Abstract: In an image processing system for processing image data which includes both text areas and non-text areas, a method for extracting image data by performing block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data, obtaining outline pairs for each text and non-text block, determining whether the circumscribing rectangles overlap, decomposing overlapped rectangles based on the outline pairs, extracting image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles, and processing the extracted image data.

Abstract: A method and an apparatus for identifying completed forms includes scanning a plurality of different blank forms, and creating hierarchical profiles of each scanned blank form. Each hierarchical form profile is stored in a dictionary. Once the form dictionary is created, a completed form is scanned. A hierarchical profile of the completed form is created, and the hierarchical profile of the completed form is compared with stored hierarchical form profiles. In accordance with the result of comparison, one of the stored hierarchical form profiles is identified as corresponding to the completed form hierarchical profile. Based on the identity of the corresponding hierarchical form profile, the completed form can be routed for further processing. A further aspect of the invention makes it possible to extract data from predesignated fields which may be unique to that particular form within a completed form based on the form's identity.

Abstract: In a character recognition system or the like, method and apparatus for selecting blocks of pixels from pixel image data so as to permit identification and grouping of similarly-typed pixels, such as text-type pixels and non-text-type pixels. Pixel image data is inputted and, if the pixel image data is not binary image data then the pixel image data is converted into binary pixel image data. Blocks of pixel image data are selected by outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text unit or non-text units based on the size of the outlined connected components, selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, and selectively connecting text lines vertically to form text blocks based on proximity of adjacent text lines and on the position of non-text units between text lines. A hierarchical tree is formed based on the outlined connected components.

Abstract: A character recognition system or the like in which character identities are stored in accordance with a hierarchical order established during processing to separate text image areas from non-text image areas. To separate text image areas from non-text image areas, blocks of pixels are selected from pixel image data by outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text units or non-text units, selectively connecting text units widthwisely to form text lines, and selectively connecting text lines vertically to form text blocks. After blocks of pixels have been so selected, text blocks are segmented into lines of pixel image data, and characters are cut from the lines of pixel image data so obtained. If desired, the characters may be cut by a two-step cutting process in which non-touching and non-overlapping characters are first cut out, and touching characters are then cut out.

Abstract: Method and apparatus for selecting text and/or non-text blocks in a stored document includes functions and structure for identifying connected pixel components in a stored document, separating the identified pixel components into text and non-text components, searching the document for visible and invisible lines along edges of the non-text components, forming irregularly-shaped text and non-text blocks using the identified text components and the visible and invisible lines, detecting the text orientation for each formed text block, extracting text lines from the text block based on the detected orientation, detecting the skew angle for the stored document based on the extracted lines, and modifying the formed text and non-text blocks based on the detected skew angle. The thus-formed text blocks are preferably subjected to character recognition routines.