Abstract: A method and system for recognizing alphabetic characters that contain diacritics is described. An image analysis separates the character into its constituent components. The one or more diacritic components are then distinguished and isolated from the base portion of the character. Optical recognition is performed separately on the base portion. The diacritic is recognized through a special image analysis and pattern recognition algorithms. The image analysis extracts geometric information from the one or more diacritic components. The extracted information is used as input for the pattern recognition algorithms. The output is a code that corresponds to a particular diacritic. The recognized base portion and diacritic are combined and a check is performed for acceptable combinations in a chosen language. By separately recognizing the base portion and diacritic, the character sets used by the recognizer can be narrowed, resulting in greater recognition.

Abstract: In document recognition processing for accurately recognition a document image at high speed, a shape feature is extracted from a component included in an input document image, and the degree of similarity of shape between the document image and the registered document is calculated based on the extracted shape feature. When it is determined that the component of the document image has color information, the color information is extracted from the document image, thus calculating the degree of similarity of color information from the document image. The degree of similarity of shape is corrected based on the degree of similarity of color information, thus determining that the registered document is similar to the document image.

Abstract: A method and system for enabling registration of a user to use a computer system. The method includes providing a printed registration form containing information relating to user registration, the form including coded data indicative of an identity of the form and of at least one reference point of the form. Indicating data is received, in a processing system associated with the computer system, from a sensing device regarding the identity of the form and a position of the sensing device relative to the form. The sensing device, when placed in an operative position relative to the form, generates the indicating data using at least some of the coded data on the form. The method further includes identifying, in the processing system and from the indicating data, at least one parameter relating to user registration, and storing the at least one parameter so as to be accessible by said computer system.

Abstract: A method and a device for detecting the occupancy state of a seat, e.g., in a vehicle, and for use in activating a restraint mechanism allocated to the seat, as a function of the occupancy state, are provided. With the aid of an image recording system, a 3D image of the seat is recorded and evaluated with respect to the occupancy state, and optionally also with respect to the type of the occupancy. For the evaluation, a 3D pattern is drawn upon, which is available externally or which is able to be generated internally in an initialization step. A hierarchically constructed evaluation also permits, after determination of an occupancy state, a classification with respect to the type of the respective occupancy.

Abstract: In an image processing apparatus, monochrome image data is printed onto a sheet and a user makes a mark in the sheet in order to specify an area. The marked sheet is scanned by a scanner. The mark is extracted from data generated by scanning. Registration is performed based on coordinates of the scanned data and the monochrome data. Based on the result of the registration, the extracted mark is represented in original image data. Accordingly, a complicated area can be easily specified so that the user can make a mark by hand.

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: Methods and system for automatic identification of repeating patterns of slanted stripe features (marks) on an item.

Abstract: Techniques for positioning images in an electronic document. The images may encode information that can be decoded by devices configured to read the images. An area within the electronic document for positioning the image and a set of one or more colors to be used for the image are determined. The determined area and set of colors are such that the image when positioned in the electronic document blends in with the contents of the electronic document while still being clearly visible for reading by reader devices that are configured read and decode the information encoded by the image.

Abstract: A method and apparatus is disclosed that can scan a page, detect the location and size of any devices or objects on the page, and then print information onto the page without printing the information onto the located devices.

Abstract: A method of extracting a textual area in a digital image, in which the digital image is divided into a plurality of blocks, each being computed to obtain a number of edges, each having a higher contrast in the block at a horizontal direction and a vertical direction. Based on the determined edge number, a plurality of textual blocks are determined out of the plurality of blocks in the digital image and the corresponding textual areas may be extracted from the digital image, so that the textual area and a continuous pictorial area in the digital image may be processed separately.

Abstract: The document generating apparatus is provided with: an acquiring unit that acquires information on a first operation on a display screen and information on a second operation on the display screen, the first operation being for designating a part area of an image as an area to be included in an electronic document, and the second operation being for setting a size of a medium on which the electronic document is printed; an adjusting unit that adjusts the part area of the image designated in the first operation into the medium of which size is set in the second operation; and a generating unit that generates the electronic document based on the image adjusted by the adjusting unit.

Abstract: A method for segmenting at least a pair of regions of an image. High resolution data is obtained of the image. Each one of the pair of the regions in the image is marked. Graph cuts are used on the downsampled data to obtain first voxels along an outer boundary of a selected one of the pair of marked regions and second voxels along an inner boundary the selected region. The graphs cuts are projected to the previously obtained high-resolution image data. First and second sets of seeds are placed on the first voxels and a second set of seeds respectively. The first seeds grow into first areas extending inwardly of the selected region while simultaneously the second seeds grow into second areas extending towards the first extending areas until the first areas and the second areas meet to thereby establish the outer boundary of the selected region.

Abstract: An image processing apparatus includes an acquiring mechanism configured to acquire an original document image, a dividing mechanism configured to divide the original document image acquired by the acquiring mechanism into a plurality of areas arranged in symmetry with respect to a center point of the original document image when the original document image is rotated centering around the center point of the original document image, a generating mechanism configured to generate verification data corresponding to the plurality of respective areas divided by the dividing mechanism, and an embedding mechanism configured to embed the verification data to the original document image in an identical scanning direction in a manner of point symmetry with respect to the center point of the original document image and to generate an encoded document image including the verification data.

Abstract: A method of and system for identifying a target form for increased efficiency in an automated data capture process is described. Forms are scanned and stored as digitized images. Regions are defined on the form relative to corresponding reference points between the form and the digitized image. The regions are defined in areas that contain anticipated digitized data from data fields of the form. Digitized data is recognized through such means as optical character recognition (OCR) and the resulting string variable is compared in form to a plurality of formats expected for that data. Scoring systems are used to obtain a resultant score for a number of string variables which is compared to a predetermined confidence number. If said confidence number is reached, the form is flagged as a target form and used in the data capture process. A first step identification of certain graphical features can be added as an initial determination as to the source of the form.

Abstract: A document processing apparatus includes a marking detection part that detects a marking written on the form from data read by a first reading part, an attribute name extraction part that extracts a character string described beforehand within or near a marking area of the detected marking as an attribute name, an attribute name detection part that detects the attribute name, extracted by the attribute name extraction part, stored in an attribute information memory and specifies the descriptive position of the detected attribute name from the data read by a second reading part that reads the form on which the attribute values are entered, and an attribute value extraction part that extracts the character string around the detection position of the attribute name detected from the read data, and registers the extracted character string as the attribute value of the attribute associated with the attribute name in the attribute information memory.

Abstract: Method of automatically sorting mail 1 which has to be forwarded by means of a sorting machine, which processes the mail 1 in a continuous main stream A and where the sorting machine comprises a feeder 2 via which a variety of unsorted addressed mail is fed. The singled mail 1 is marked with an individualising identifier by a following marking device. Each identifier is assigned to a data set in a file, and by means of a following reading device 5 the addresses on the mail 1 are taken up. A taken-up address is deciphered by a recognition module and is written in the corresponding data set. The mail 1 is assigned a corresponding error information when the address cannot be deciphered. A mail piece with assigned error information is then sorted out of the main stream as scrap mail 6.

Abstract: A method and an apparatus for segmenting contours of objects in an image is disclosed. It particularly applies to the segmentation of body organs or parts depicted in medical images. An input image containing at least one object comprises pixel data sets of at least two dimensions. An edge-detected image is obtained from the input image. Markers are selected in the edge-detected image, and assigned respective fixed electrical potential values. An electrical potential map is generated as a solution to an electrostatic problem in a resistive medium having a resistivity dependent on the edge-detected image, with the markers defining electrodes at the respective fixed potential values. Object contours are estimated, for example by thresholding, from the generated potential map.

Abstract: A system for determining anatomical landmarks is disclosed. The anatomical landmarks can be used to determine anatomical targets of a patient. The system can allow for the detection of landmarks in the brain or other appropriate anatomical regions.

Abstract: A method is provided for segmenting scanned image data in accordance with mixed raster content processing, further including windowing for purposes of extracting particularly classifiable objects, i.e., text, graphics or pictures. Application of predetermined parameter sets selected for more precise identification of the extracted objects are applied to the data for object extraction, object selection, color uniformity, and clustering for coloring similarity. A page background detection feature uses dual thresholding for segregating text (darker) areas from non-text (brighter) areas. Two histograms are created for the respective areas. Thresholds are generated from the two histograms and applied to the respective areas separately.

Abstract: A method to secure unique information about a handwritten document and to provide verification of document's authenticity, integrity and non-repudiation. The method includes the following steps: creating a document having an area of interest containing information, segmenting the area of interest on the document into a plurality of elements, obtaining the average gray scale of each element, inserting the average gray scale of each element into an identifier, and attaching the identifier to the document.

Abstract: An image evaluating apparatus capable of evaluating photographic images with expressions that approach human perception is provided. A boundary extracting means extracts boundaries among subjects from a digital photographic image in which a plurality of subjects are pictured. An image region extracting means extracts image regions, which are divided by the boundaries. An image region position judging means determines which of a plurality of sections each image region is included in. An image region feature judging means judges the features of subjects pictured within each image region. An image evaluating means evaluates the digital photographic image, based on the extracted boundaries, the sections in which each image region is included, and the features of the subjects pictured within each image region.

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: An image processing apparatus includes: an image decomposition unit that decomposes an input image into component images constituting the input image; a confidentiality setting unit that sets a confidentiality being a degree of security of each of the component images into which the input image is decomposed by the image decomposition unit; and a storage unit that stores each of the component images by associating the confidentiality therewith, the confidentiality being set by the confidentiality setting unit.

Abstract: This invention is a support technique for enabling the easy correction of the ruled lines and cells, which are automatically extracted from the form document image or the like. This invention includes: generating plural candidate cells from an image of a table including plural cells, and outputting an initial table by extracting a specific combination of the candidate cells; accepting, as designation of an error cell, designation of a specific candidate cell included in the initial table from a user; generating a candidate group by selecting the candidate cell that can replace at least a portion of the designated error cell, from the candidate cells other than the specific combination of the candidate cells; and presenting the candidate group for the user, and prompting the user to select one of the candidate cells included in the candidate group.

Abstract: Disclosed is an image processing apparatus in which a marked image is extracted more accurately and classification based upon the type of mark is made possible. The apparatus includes an extraction unit adapted to extract information representing a region position of an object and information representing a region position of a mark as an object list and mark list, respectively, from the document image that has been scanned by a scanning unit; and a search unit adapted to search for information representing the region position of a mark in the mark list for which the distance is the shortest with respect to information representing a region position of each object in the object list.

Abstract: A document segmentation method of detecting segmentation points where a topic of an input document is discontinuous before and after the point to divide the document into plural blocks includes: detecting terms that occur in an input document; segmenting the input document into document segments, each segment being an appropriate sized chunk; generating document segment vectors with as its elements values related to frequencies of the terms occurring in the document segments; calculating eigenvalues and eigenvectors of a square sum matrix of the document segment vectors; selecting the basis vectors consisting a subspace from the eigenvectors to calculate the topic continuity of the document segments; calculating vectors with as their elements the values corresponding to the projection values of the each document segment vector onto the basis vector; and determining segmentation points of the document based on the continuity of the projected vectors.

Abstract: A method and system for performing image mark recognition for a document is disclosed. A document is scanned into a digital image. Reference image marks are sensed from the digital image. The reference image marks may include trigger row marks and/or corner/crop marks. Coordinates denoting the location of cells within the digital image are determined based on the locations of the reference image marks. Response marks are evaluated for darkness, opacity, and/or grayness on a pixel-by-pixel basis. The response marks are each assigned a percentage value based on the ratio between a total color value for a cell and a maximum color value for a cell.

Abstract: An imaging system (110) for imaging a scene with a detector array (104) having an array of imaging elements is provided. The imaging system (110) includes an image estimation module (202) for generating a plurality estimates of uncorrupted images based upon a plurality of noisy images generated by the detector array (104). The imaging system (110) further includes a parameter determination module (204) for determining one or more nonuniformity correction parameters based upon the estimates of uncorrupted images.

Abstract: Correlation between images and photography locations thereof is facilitated when generating an album of images photographed during a trip. Map data sets are stored in a storage means of an album generation support server. A user accesses the album generation support server from a personal computer to request album generation. Screens for transmitting image data sets and for prompting input of data that specifies a travel route are displayed at the personal computer. The user inputs data regarding a departure point, a departure time, a final destination, etc., and transmits the image data sets to the album generation support server. An album generation server generates travel route data representing the user's travel route based on the input data, estimates locations along the travel route where the image data sets were photographed based on time data attached thereto, and generates album data by correlating the image data sets with a map.

Abstract: A method for determining a border of an image includes (a) receiving a composite image including a background image and a foreground image, (b) following one geometric feature (e.g., a line) of the background image, and (c) detecting two or more breakpoints in the first geometric feature where the foreground image superimposes the geometric feature. Actions (b) and (c) are repeated to detect breakpoints for a number of the geometric features. The border of the foreground image is determined by constructing linear edges that each connects three or more breakpoints and extending the linear edges until each intersect with two other linear edges to form the border of the foreground image. An apparatus for determining a border of an image includes a scanner and a document cover. The document cover includes a blue backdrop and geometric features. The geometric features include green vertical and horizontal lines.

Abstract: Additive information for restoring the contour of an image is generated and embedded in the image data. The format of the additive information is determined beforehand. When a hard copy is produced, the additive information is extracted from received image data. The additive information is for example vary small characteristic points of a density different from the density assigned for image data and arranged inside the contour. The image data is restored according to the extracted additive information. The additive information can be generated for example from the code information for generating patterns such as control points data of an outline font. For a half-tone image, a plurality of density bands is assigned to the additive information. A read error is detected by comparing the restored image with the received image data.

Abstract: A white background determination section performs a white background determination on the basis of a white threshold calculated by a white threshold calculation section and an area size selected by an area size determination section. A character discrimination section executes character recognition such that a condition for character discrimination is relaxed when the white background determination section determines that a pixel of interest belongs to a white background, and the condition for character discrimination is made stricter in other cases.

Abstract: With this invention, upon scanning a print, since additional information recorded together with that print is reproduced while displaying the scanned image, a special effect that cannot normally be obtained from still images can be obtained. A print on which image information and additional information, different from the image information, are printed is scanned by a scanner (209). An additional information demultiplexer (210) demultiplexes that additional information, which is decoded by an error correction decoder (211). After that, the image and the decoded additional information (moving image or/and acoustic information) are simultaneously reproduced in combination.

Abstract: Table-like structures in documents are located by analysis of sub-regions (crops) on the document. The analysis involves determining the location of lines having lengths above a certain threshold and assigning these lines to groups. A set of adjacent lines is assigned to a common group if the separation between adjacent pairs of lines within the set is less than a threshold value. The crop selected as the location of the table-like structure is that having a group with the greatest number of lines. When the technique is applied to locating title blocks in technical drawings, it is preferred to analyze crops corresponding to the corners or ends of the document. The analysis is also applicable to an image of the document produced at a reduced resolution.

Abstract: An image processing apparatus includes an image capturing section, a marker-image defecting section, a judging section and an output section. The image capturing section captures at least a part of a target image, which includes a plurality of marker images and a recognition target range defined by the plurality of marker images, to acquire a captured image. The marker-image detecting section detects the marker images from the captured image. The judging section judges based on a detection result, whether or not the recognition target range is included in the captured image. When the judging section judges that the recognition target range is not included in the captured image, the output section outputs guidance for capturing the recognition target range.

Abstract: An image processing apparatus captures a target image containing marker images and a recognition target range identified by a marker-image set including at least parts of the marker images. The image processing apparatus includes an image capturing section, a first detection section, a position estimation section and a second detection section. The first detection section detects one marker image as a reference marker image from a captured image. The position estimation section adopts a marker image, which is other than the reference marker image and is contained in at least one of marker-image sets containing the reference marker image, as a corresponding marker image. The position estimation section estimates a position of the corresponding marker image in the captured image based on a size of the detected reference marker image. The second detection section detects the corresponding marker image based on the estimated position of the corresponding marker image.

Abstract: The invention relates to a method of editing data generated by handwriting. The method comprises the steps of detecting an initiation of an editing; identifying a marking stroke which marks data that is to be edited; determining an essentially minimal convex envelope which surrounds the marking stroke; identifying the remaining data, in addition to the data of the actual marking stroke, which is positioned within the convex envelope; and performing an editing operation on said data positioned within the convex envelope. The invention also relates to a handheld device and a computer program for editing of data generated by handwriting.

Abstract: A character overlapping with a line of an entry box is extracted utilizing a dot box. At document input step S2, a document to be recognized is read and converted into electronic data to produce character box data. At electronic data storing step S3, the character box data read at the photoelectric transducing S2 is stored. At character detecting step S5, the character box data is contracted, small points are removed, and the remaining pattern is reversely expanded to produce character data. At entry box detecting step S4, entry box position data is generated from the character box data and character data. At relating step S6, a character pattern entered in each entry box is detected from the character data and the entry box position data. At character recognizing step S7, a character is recognized for the extracted character pattern and the results are stored at step S8.

Abstract: An image processing apparatus including a receiving unit, an extraction means, and a conversion means is disclosed. The receiving unit receives a first document data and a second document data obtained by reading respectively a first document and a second document each having at least one drawing. The extraction means extracts a first caption group for identifying the drawing contained in the first document and a second caption group for identifying the drawing contained in the second document. The conversion means converts the first caption group and the second caption group into a third caption group so that a character string in the first caption group does not overlap a character string in the second caption group.

Abstract: A segmentation method receives a learning image and an objects of interest specification. A segmentation learning method creates a segmentation recipe output. It performs a segmentation application using the second image and the segmentation recipe to create a segmentation result output. The segmentation learning method includes an object region of interest segmentation learning step and an object type specific segmentation learning step. The segmentation application method includes an object region of interest segmentation step and an object type specific segmentation step. The learnable object segmentation method further comprises an online learning and a feedback learning step that allows the update of the segmentation recipe automatically or under user direction.

Abstract: A logical separation between pages, such as an implicit page break, is introduced to separate text entered during one handwriting session from text entered during another handwriting session. The amount of time elapsed since ink has been captured on the previous page is a factor that may be used to determine whether to insert an implicit page break into the new page. A change in context, such as a different date or different recognized subject matter labels, is also a factor that may be considered in determining whether to insert an implicit page break.

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 printer controller generates pattern data to be printed by a printer engine for use in carrying out a tone adjusting process. The printer controller includes a memory which stores reference tone patterns and tone adjusting patterns, a selecting section for selecting a dot size of one of the reference tone patterns to be printed, the dot size being determined by a number of pixels forming each dot, and a generating section for generating and outputting to the printer engine the one of the reference tone patterns by the dot size selected by the selecting section and tone adjusting patterns having tones falling within a predetermined range with respect to a reference tone of the one of the reference tone patterns, based on the reference tone patterns and the tone adjusting patterns stored in the memory.

Abstract: An image upscaling algorithm jointly optimizes estimating pixel color, classifying it into one of multiple regions, and estimating region boundaries subject to region continuity and edge-configuration constraints. The joint solution of constraints at multiple levels of image abstraction leads to improved image reconstruction quality. The algorithm involves subdividing the image signal into multiple distinct regions, including an upper region and a lower region, and at least one transition zone between the upper and lower regions; constructing a plurality of separate curves, one for each region; smoothing each curve independently of the other curves; and reconstructing the image signal from the smoothed curves such that the reconstructed image signal has no segment in any transition zone.

Abstract: A computer system and method relating to editing an electronic document having both text and drawings is disclosed. Drawings may be rescaled and/or repositioned responsive to a change in line height or font size of text. The resealing may be done in proportion to the change in line height or font size, and the repositioning may be performed to avoid overlapping of the rescaled drawings. A document may be divided into a plurality of adjacent regions, and drawings within the document may each have an offset value representing a distance between the drawing and a reference axis of one of the regions.

Abstract: Image capture device control marks are automatically generated within a computer or printer and automatically printed on pages output from the printer. The control marks when detected by a control mark capable image capture device communicate information to the image capture device such as which areas of the printed page are text that require optical character recognition, which areas of the page are photos that require high-resolution full-color, which areas of the page are line drawings that require medium-resolution black and white, and which areas of the page are not to be scanned. Image capture device control marks may be configured in a wide range of sizes, styles, and locations on the printed page.

Abstract: Suppression of one or more features in an image of a page of content may be achieved by acquiring a page image, identifying one or more features in the page image that are to be suppressed or not to be suppressed, and preparing a substitute page image which only includes images of the features that are not to be suppressed. Preparing a substitute page image may include generating a blank image and using location and size information to copy images of the non-suppressed features from the original page image to the blank image. In other embodiments, preparing a substitute page image may include removing image information from the original page image outside the non-suppressed features, or identifying and removing features that are to be suppressed from the original page image. Feature suppression may be used to implement access rules that limit the content in a page image.

Abstract: In the case of private scan, an entire control section saves, on a hard disk device, “setting information/data” for scan as a record, and reads, when necessary, “setting information/data” saved as a record on the hard disk device, thereby registering it as a template.

Abstract: In a color conversion section 10a, a mode judging section 31 judges a mode in effect: a copy mode or a printer mode, according to a mode judging signal. When the copy mode is identified, the mode judging section 31 supplied RGB data to a first color conversion process section 32, and the first color conversion section 32 carries out a first color conversion process in which a transitional color conversion value, which is color-transited from a precise color conversion value and a memory color conversion value, is set as a color conversion value with respect to memory color corresponding data. When the printer mode is identified, the mode judging section 31 supplies the RGB data to a second color conversion process section 33, and the second color conversion process section 33 carries out a second color conversion process in which the memory color conversion value is set as a color conversion value with respect to the memory color corresponding data.

Abstract: A table image processing device processes a table image and a memory medium stores a processing program. The table image processing device processes precisely a table image containing a round corner and includes a device extracting a line extracting a longitudinal line and lateral line out of an input image, a device finding a potential match of a round corner region extracting an oblique line which commences from a terminal of a line found by the line extracting device, and finding the potential match of the round corner region, a device extracting a cell containing the potential match of the round corner found by the potential match of the round corner region finding device, and a device deciding the round corner part deciding the round corner from the cells found by the device extracting the cells.