Abstract: Methods and systems for motion adaptive filtering detect movement of text or areas of high spatial frequency in one frame to another frame of an image. When such movement is detected and meets a certain level or threshold, the subpixel rendering processing of such text or areas of high spatial frequency may be changed.

Abstract: An information processing apparatus includes feature extraction means for extracting features of a designated image in plural images which are associated with each other, image determination means for determining whether the designated image is an image of the face of a certificate, a receipt, a ticket or a note on which a character string is written based on the extracted features, and metadata addition means for adding the first metadata which is character string data of the character string to another image in the plural images, when it is determined that the designated image is an image of the face of a certificate, a receipt, a ticket or a note on which a character string is written.

Abstract: Pattern matching can be achieved by considering only the position numbers of a source pattern and a target pattern within ordered sequences of possible source patterns and target patterns respectively. The position numbers of source patterns containing the target pattern form a number of groups. The number of source patterns within each group and the number of source patterns in the gaps between groups depend on the position of the target pattern within the source pattern, the length of the target pattern and the number of elements in the alphabet set. Each group also has a position number, its position within an ordered sequence of groups. The group position number of an input source pattern is compared to a series derived from the position number of the target pattern, the length of the target pattern and the number of elements in the alphabet set (9). If the group position number is a member of the series (10), then the source pattern contains the target pattern (11).

Abstract: A form processing apparatus extracts layout information and character information from a form document. A candidate extracting unit extracts word candidates from the character information. A frequency digitizing unit calculates emission probability of a word candidate from each element. A relation digitizing unit calculates transition probability that relationship between word candidates is established. An evaluating unit calculates an evaluation value indicative of a probability of appearance of word candidates in respective logical elements. A determining unit determines the element and a word candidate thereof as the element and a character string thereof in the form document, based on the evaluation value.

Abstract: Systems and methods that exploit unique properties of a language script (e.g., condition joining rules for Arabic language) to enable a two tier text recognition. In such two tier system, one tier can recognize predetermined groups of linked letters that are connected based on joining rules of a language associated with the text, and another tier dissects (and recognizes) such linked letters to respective constituent letters that form the predetermined group of linked letters. Various classifiers and artificial intelligence components can further facilitate text recognition at each level.

Abstract: A method and apparatus for use with a navigation system allows a user to easily and quickly input an address of a destination with use of a specially made database even when spelling of the address is not certain to the user. The navigation system is designed to help the user in entering a desired street name accurately and efficiently by checking candidate cities when a first character of street name is specified. Since the user accurately knows at least the first character of the intended street name, the candidate street names will be narrowed down by selecting the city. The user may further input second character and further characters upon which the navigation system incrementally retrieves candidate street names with use of the comprehensive alphabetical usage file.

Abstract: A device comprises first frequency calculating means (142) for calculating a function value IDF(P) of the frequency of an index word in a document (d) to be examined in a group of documents (P) to be compared, second frequency calculating means (171) for calculating a function value IDF(S) of the frequency of the index word in a group of similar documents (S) similar to the document (d), coordinate transforming means (181) for transforming the position of each index word by conformal mapping on a coordinate system where the calculated function value IDF (P) goes on a first axis of the coordinate system and the calculated function value IDF(S) goes on a second axis, and output means (4) for outputting the index words and their positioning data according to the transformed coordinate data of the index words. With this, the character of the document is accurately expressed, or the tendency of the whole of the documents group to be examined can be analyzed.

Abstract: It is an object of the present invention to provide an image processing apparatus having a function to store print data in a searchable manner. In order to achieve the object, when print data including a bitmap image and attribute data of each pixel of the bitmap image is received, meta data is generated by executing a character recognition processing based on pixels having a character attribute in the attribute data. Further, vector data indicating a character outline is generated. Then, a document including meta data and vector data is generated.

Abstract: An original image data representing an image read out from an original is removed with noise of a predetermined periodic pattern, if any, and storage image data is generated. The storage image data is stored in an image memory and is subjected to an enlargement/reduction processing and output image data is generated. An image is reproduced on the basis of the output image data.

Abstract: A method for digitizing images stored on film material has, after the image conversion by means of a digitizing device firstly an electronic color value correction independent of user inputs. A user-controllable correction and manipulation of the electronically stored information is subsequently carried out only after the electronic color value correction, which is effected in a manner dependent on properties of the digitizing device and on film material properties. The electronic color value correction depends on parameters which can be adapted to varying properties of the digitizing device. A film scanner adapted to this method has a digitizing device and also a device for controllable correction of the converted image data. A device of discrete construction for electronic color value correction is connected between the digitizing device and the device for controllable correction.

Abstract: A meter is read. An image on a face of the meter is captured. Optical character recognition of digits of a digital display on the face of the meter is performed. At least one stored template is used to perform the optical character recognition of digits.

Abstract: A certification photograph creation system includes a certification photograph taking apparatus, an image input apparatus to input a photographed image, an image processing apparatus and a printer to output an image that has been subjected to the image processing as a certification photograph. The certification photograph taking apparatus includes an input device to input an identification code that indicates a use of a print and optionally a print size. The image taking apparatus, the image processing apparatus and the certification photograph creation system are capable of simplifying the processes of taking and/or creating the certification photograph.

Abstract: An automated symbolic recognition system and method includes multiple representations of each alphanumeric in the database by identifying a finite number of exemplars per alphanumeric symbol.

Abstract: The invention relates to a mobile device with a built-in image capture device, and a character recognition function to present the information gathered with the character recognition result. With the mobile device, the character line extraction process is displayed whenever necessary, and the resolution of an image to be inputted for recognition processing is enhanced. Accordingly, it is possible for the operator to select the target character line with ease. In addition, the mobile device has a character recognition ratio improved by the enhancement in resolution.

Abstract: Finite-state systems and methods allow multiple input streams to be parsed and integrated by a single finite-state device. These systems and methods not only address multimodal recognition, but are also able to encode semantics and syntax into a single finite-state device. The finite-state device provides models for recognizing multimodal inputs, such as speech and gesture, and composes the meaning content from the various input streams into a single semantic representation. Compared to conventional multimodal recognition systems, finite-state systems and methods allow for compensation among the various input streams. Finite-state systems and methods allow one input stream to dynamically alter a recognition model used for another input stream, and can reduce the computational complexity of multidimensional multimodal parsing.

Abstract: This invention re-encodes encoded data (e.g., PackBits encoded data), which is expressed by a data format of a runlength code part indicating the runlength of the same data and a data part indicating the data, and a runlength code part indicating the runlength of a different data stream and a data part indicating the different data stream, to the same data format without decoding that encoded data, thereby improving a compression ratio. To this end, upon reception of data encoded by a PackBits encoding process, a data division unit separates that data into information indicating the runlength of data, and a data part, and outputs them as num and data. A data processing unit masks a predetermined bit in accordance with an instruction from a monitor unit, and outputs that result to a data combining unit. The data combining unit and a data output unit reconstruct and output data in the PackBits format in accordance with the masked data part and num data.

Abstract: A character display device and method therefor are adapted to obtain a proximal reference point of each character comprising a character series and calculate display coordinates of each character from said proximal reference point and the display angle and display reference position of the character series.

Abstract: The image processing apparatus subjects input image data to predetermined image processing to create output image data to be output as a print. The processing apparatus includes an extracting device for extracting a main subject from the input image data and a first determining device for determining a print magnification and a frame position in accordance with a size of the extracted main subject and a previously designated print size. The processing apparatus optionally includes a second determining device for determining a use of the print from an identification code input when a photograph is taken. The certification photograph taking apparatus includes an inputting device for inputting an identification code indicating a use of a print and optionally a print size.

Abstract: A feature extractor samples points on an input pattern drawn in real time. In addition to X and Y coordinates, each sample has an up/down or Z coordinate value representing whether or not the sample point is a perceptible part of the pattern. The groups of coordinate values are transformed into respective sets of coefficients of Chebyshev polynomials by least-squares fit. A recognition unit can use the coefficients as features to identify the character. Additional features, such as aspect ratio and center of gravity, are also derived to aid in recognizing the pattern or reconstructing its image.

Abstract: A word recognizing apparatus extracts the feature amount from a given image, and dynamically composes the feature amount of a candidate word to be recognized which is registered in a word list, using feature amounts of characters registered in an individual character dictionary. Then, the apparatus collates the composed feature amount of the word with the feature amount extracted from the image, calculates the degree of similarity between the two feature amounts, and outputs a recognition result.

Abstract: A method for recognizing handwritten Chinese characters based on stroke recognition comprises steps of: recognizing handwritten strokes, updating stroke code sequences; retrieving in dictionaries/lexicons at least one corresponding character/phrase entry so as to obtain at least one candidate Chinese character/phrase; dynamically displaying the at least one candidate Chinese character/phrase; jumping to the step of recognizing strokes if it is judged that a next stroke is being written; inputting a displayed Chinese character/phrase into computers as the result of recognition if this character/phase is selected by the user.

Abstract: An apparatus, system, and method are disclosed for creating an electronic description of a geographic site. The apparatus, system, and method beneficially facilitate rapid capture, digitization, and creation of the electronic descriptions, which are advantageously smaller in storage size and widely distributed among users. The apparatus for creating an electronic description of a geographic site includes an electronic drafting program, a digitization module, and a capture module. The electronic drafting program is configured to import an image file, the image file comprising a plurality of image elements, and to electronically trace at least one of the image elements, which creates a tracing element. The digitization module is configured to associate definition data with the image element. The definition data is descriptive of the image element. Subsequently, the capture module stores at least the tracing element and corresponding definition data in a capture file.

Abstract: An “activity”-based system and method for on-line character recognition that requires reduced amounts of memory for code or data, is alphabet-independent, and can be trained by entering the alphabet once. The alphabet-independent nature of the algorithm, as well as the ease with which recognition may be optimized dynamically, makes it particularly well suited for writing in noisy environments (e.g., mobile or on a subway) or by persons with impaired motor skills or nervous conditions.

Abstract: A method for extracting text from images whereby the intensity of each color plane of the image is identified, the color plane with the highest intensity is converted into a black and white image, and character recognition is performed on the black and white image to determine the text of the image. The method can be used for textual word searches for Graphics Image Format (GIF) images as well as Joint Photographic Experts Group (JPEG) images, thereby providing the capability to perform text searches for images found on web pages of the World Wide Web.

Abstract: Systems and methods are provided for automatically determining the font of text in a captured document image. Sequences of turns (left, right, straight) around the boundaries of connected components of black pixels in the captured document image are determined. The probabilities of the sequences of turns have come from a particular font within a library of known fonts can be determined using training set statistics. Using these probabilities, the most probable source font is selected.

Abstract: A method of recognizing characters of a document including ruled lines. After separating the characters from the ruled lines, a bounding box and a corresponding character pattern are extracted for each character (hereinafter, “the character”). Contour information and ground (white pel area) information are extracted as fundamental features from the character pattern. Various statistical features are extracted based on the fundamental features. Various structural features are extracted based on the fundamental features and the character pattern. On the basis of the extracted statistical features, some candidates for the character and corresponding degrees of similarity are found to provide at least such one of the candidates as has largest degree(s) of similarity and degree(s) of similarity associated with the provided candidate(s).

Abstract: A system and method for translating a written document into a computer readable document by recognizing the character written on the document aim at recognizing typed or printed, especially hand-printed or handwritten characters, in the various fields of a form. Providing a pixel representation of the written document, the method allows translating a written document into a computer readable document by i) identifying at least one field into the pixel representation of the document; ii) segmenting each field so as to yield at least one segmented symbol; iii) applying a character recognition method on each segmented symbol; and iii) assigning a computer-readable code to each recognized character resulting from the character recognition method. The character recognition method includes doing a vector quantization on each segmented symbol, and doing a vector classification using a vector base. A learning base is also created based on the optimal elliptic separation method.

Abstract: A method for encoding handwritten symbols operates upon penstroke data received from a device capable of sampling a stylus position at discrete intervals. Each handwritten symbol is segmented into an ordered sequence of discrete strokes. An are length and initial and final tangent angles are evaluated for each of these strokes. Each stroke is encoded in the form of a parameter set comprising position coordinates of the initial and final endpoints of the stroke, the arc length, and the initial and final tangent angles. In specific embodiments of the invention, the segmentation is based, in part, on properties of the handwritten symbol when it is expressed as a curve &phgr;(s), wherein s represents arc length and &phgr; represents the net turning angle.

Abstract: A line-direction deciding device that can decide the direction of lines in an image having a complicated layout of characters as well as line directions other than vertical and horizontal line directions. The present invention provides a line-direction deciding device that extracts character elements (image components) from an image, examines in which direction the character elements are most densely distributed and decides by majority the direction of lines of characters within a processable area as well as an image inclination correcting device that corrects an image for inclination according to a processing result made by the line-direction deciding device provided with image-inclination detecting means.

Abstract: Systems and methods are provided for automatically determining the font of text in a captured document image. Sequences of turns (left, right, straight) around the boundaries of connected components of black pixels in the captured document image are determined. The probabilities of the sequences of turns have come from a particular font within a library of known fonts can be determined using training set statistics. Using these probabilities, the most probable source font is selected.

Abstract: An apparatus for recognizing visual patterns of handprinted characters or the like by means of an optical character reader which reads the patterns by a so-called outermost point method. While tracing the contour of the pattern stored in a two-dimensional memory, the distances from the starting point of the tracing and the integrated values of the coordinates of the points traced on the contour from the starting points are simultaneously obtained successively to extract outermost points for the series of contours. According to this outermost points, the contours are segmented into the convex line segments, concavity line segments and hole segments and the corresponding parameters of features of each segment are detected. Simultaneously, the convex line segment of which is shorter than a predetermined length is rejected and the remaining segments are subjected to matching operation in accordance with preliminarily prepared dictionary, thereby making a decision as to the pattern's identity.

Abstract: An on-line handwritten Chinese character recognition apparatus based on character shapes uses a reference file for look-up of compressed codes-sequence codes in a conventional input method founded on dismantling by character shapes as reference when comparing character to reduce the number of matching templates required in the on-line handwritten Chinese character recognition system and to lower the time for matching. Input handwritten Chinese characters are dismantled into constituting radicals. Thereafter, with reference to code retrieving rules of the input method, and based on the character composing method of handwritten characters, radicals for comparison are retrieved. Then, the compression formula of the input method is used to compress the codes of the base radicals, and the compressed codes are compared with contents of the input method reference file to obtain the sequence codes of candidate characters.

Abstract: A line-direction deciding device that can decide the direction of lines in an image having a complicated layout of characters as well as line directions other than vertical and horizontal line directions. The present invention provides a line-direction deciding device that extracts character elements (image components) from an image, examines in which direction the character elements are most densely distributed and decides by majority the direction of lines of characters within a processable area as well as an image inclination correcting device that corrects an image for inclination according to a processing result made by the line-direction deciding device provided with image-inclination detecting means.

Abstract: A method for deriving character features in a character recognition system for recognising characters, such as letters and digits, and a character recognition system in which the method is applied. After deriving a character description from a recorded image pattern of a character to be recognised, a unique point Pi of said character description is appended, by means of a distance transform, to each point Ri of a subset R={Ri/i=1, - - - ,N} of preselected reference points in the plane of said image pattern. Feature values of one or more features possessed by the character description in each appended unique point are then determined. If the character description is a contour description, the unique point Pi appended to each reference point Ri is that point where the reference point Ri has the shortest distance D(Ri) to the contour of the character, and the character features selected are the shortest distance D(Ri) and the direction H(Ri) of the contour in the appended point Pi.

Abstract: A method for classifying and recognizing patterns which includes producing a pattern to be classified and recognized of an m-dimensional object. The object to be classified and recognized is provided in the form of an m-dimensional traverse. The method also acquires a property represented by an s-dimensional value for selected points of the traverse, whereby the s-dimensional value reflects a relationship between a respective selected point and a point preceding it and a point succeeding it on the traverse, links the s-dimensional values for the selected points of the traverse in such a manner that an overall property represented by a q-dimensional value characterizing the traverse is obtained, and smooths the traverse in order to form a new traverse.

Abstract: When a host transfers only an image to a printing apparatus to make it print out the image, a heavy load is imposed on the host, and the data size to be transferred is large, resulting in a long processing time. To prevent this, when a document is to be printed, the driver on a host sends character codes of characters that occur for the first time in that document and corresponding character images to the printer in advance, and registers them. After this process, the driver transmits, to the printer, characters as character codes, ruled lines as coordinate data representing their corner points, and data other than characters and ruled lines as mapped images. The printer maps an image on a page memory, maps characters as images with reference to the registered character codes and images, and superposes the mapped character images on the image mapped on the page memory. Also, the printer maps ruled lines based on their vertex positions, and synthesizes them on the already mapped image.

Abstract: Font attributes of characters or letters are estimated by an optical character recognition system using character, run or stroke-based techniques with or without character identification information.

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: An image processing apparatus includes an image input device for photoelectrically converting a document image which has been optically read and for inputting the converted document image as image data. An area separator separates a plurality of areas included in the input image data from one another and a character recognition is performed from a plurality of directions with respect to character data in the image data input by the image input device with reference to a character recognition dictionary. The apparatus performs a first discriminating function of discriminating, for the plurality of areas separated by the area separator, respective reliabilities in a plurality of directions on the basis of results of the character recognition, and second discrimination function for discriminating a document direction on the basis of average values of the reliabilities discriminated by the first discriminating function.

Abstract: Font attributes of characters or letters are estimated by an optical character recognition system using character, run or stroke-based techniques with or without character identification information.

Abstract: A system and method for processing stroke-based handwriting data for the purposes of automatically scoring and clustering the handwritten data to form letter prototypes. The present invention includes a method for processing digitized stroke-based handwriting data of known character strings, where each of the character strings is represented by a plurality of mathematical feature vectors. In this method, each one of the plurality of feature vectors is labelled as corresponding to a particular character in the character strings. A trajectory is then formed for each one of the plurality of feature vectors labelled as corresponding to a particular character. After the trajectories are formed, a distance value is calculated for each pair of trajectories corresponding to the particular character using dynamic time warping method. The trajectories which are within a sufficiently small distance of each other are grouped to form a plurality of clusters.

Abstract: A method for pattern recognition of indicia composed of alphabetical characters of a language in the form of at least a part of a word. The shape of each character in a word is established by means of a pattern shape recognizer. A probability value designating the relative confidence in the recognition of the character as one of the language characters is assigned to each character. The established shapes of the characters are then sequentially applied to a linguistic recognizer for further processing and the probability values of language structure to each of the language characters is assigned. Then the probability values assigned to the characters in the shape recognizer is combined with the corresponding probability values assigned to the characters in the linguistic recognizer and the path between characters possessing the highest probability values is determined.

Abstract: The present invention provides a method and an apparatus for reliably detecting the upside and downside vertical direction of an image, such as characters on a document. The method involves judging the upside and downside vertical direction of the characters in each line, and specifying the upside and downside vertical direction of the characters on the entire image on the basis of the vertical directions detected line by line.

Abstract: A feature extracting unit extracts an input feature vector from an input character pattern. A learning unit computes orthonormal bases of a partial eigenspace of an original feature space from learning feature vectors of a plurality of learning character patterns, and stores the computation results in an orthonormal base storage unit for the partial eigenspace. The learning unit computes each of the dictionary selection feature vectors prescribed in the partial eigenspace corresponding to each of the object character patterns, and stores the computation results in a recognition dictionary unit. A feature selection unit computes an input selection feature vector obtained by projecting an input selection feature vector extracted by the feature extracting unit on the partial eigenspace using the above described orthonormal bases. A collating unit estimates a type of the input character pattern by collating the above described input selection feature vector with each of the dictionary selection feature vectors.

Abstract: A method and apparatus to recognize hand-printed characters represented as an electronic ink stream. A first filtering box (300) is defined around a center of a first output point (324) in the electronic ink stream and the first output point is added to a filtered ink stream. A second output point (328) is added to the filtered ink stream only when the electronic ink stream moves outside the filtering box (300). When the second output point (328) is added, the filtering box is re-centered on the second output point (328) only in a dimension that is exceeded after adding the second output point (328) to the filtered ink stream to create a second filtering box (310). Moreover, extraction points (630, 640, 650 and 660) are provided approximately equally spaced across a finite set of points of electronic ink to create a compact representation of a finite set of points of electronic ink.

Abstract: The current invention is directed to further improve the character recognition process based upon the comparison of identification value in a sample image and a reference image by adjusting the identification value of the sample image. The adjustment is made based upon a predetermined feature of the sub-area or a mesh region of the images. The desired improvement in accuracy is obtained especially for recognizing handwritten characters.

Abstract: A method is described for the automatic recognition of at least one handwritten symbol. A representation of such symbol is provided, in a data storage medium, as a sequence of one or more discrete strokes having respective initial and final endpoints, a spatial location and a tangent angle being associated with each endpoint. Representations of plural library symbols, each a prototype of a possible class to which the input symbol may be assigned, are retrieved from a data storage medium. A comparison between the input-symbol representation and each of the retrieved library symbol representations includes comparing the respective tangent angles of the input symbol with the corresponding tangent angles of at least some of the library symbols, and comparing the respective endpoint locations of the input symbol with the corresponding endpoint locations of at least some of the library symbols.

Abstract: In an image processing method, contours of an image are represented in the form of vector coordinates, and calculation processing is performed based on the vector coordinate representation. In the method, noise present within the original image from which the vector coordinates are extracted is removed in the form of vector data.

Abstract: Pre-recognition analysis on stroke characteristics such as the count, size and position of each stroke in real-time as it is drawn improves recognition accuracy. After each stroke, the set of strokes is weighted toward handwriting or gesture. The system uses a gesture threshold size to distinguish between gestures and handwriting. The system also uses the stroke count to distinguish between the two inputs, relying on the knowledge of the allowable number of strokes in a gesture. The count information may also be used in conjunction with the stroke size information to weight the set of strokes between gestures handwriting. Once the stroke size crosses a gesture vs. text size threshold, the result is weighted toward gestures. By examining the `white space` between strokes and the juxtaposition of the strokes, a gesture vs. text determination can be made with high accuracy.

Abstract: To distinguish between gestures and handwriting, the pen subsystem examines the size of the user's writing. The user may set the gesture versus text size according to his/her handwriting style. In this manner, the user knows exactly how large to make the gestures. If the user declines to customize the setting, the pen subsystem can query other user settings that indicate approximate size of the user's handwriting. A third choice available the system dynamically determine and track the size of handwriting. This would allow multiple users to serially use the computer without having to change settings.