Abstract: A pen-based computer text input system capable of interpreting a special pre-defined set of single stroke glyphs. Each input stroke is identified with one of three categories: (1) pre-character modifier strokes, (2) character or symbol strokes, or (3) post-character modifier strokes. Pre-character modifier strokes precede character strokes and inform the present recognition system that a subsequently entered character stroke is to be modified by the pre-character modifier stroke in a pre-defined manner. Character strokes cause a character or symbol to be displayed on the display device the moment it is input on the writing tablet, interpreted in accordance with any pre-character modifier stroke. A post-character modifier stroke causes the recognition system to modify, in a pre-defined manner, a character or symbol which was previously entered and displayed. An important advantage of the present invention is its ability to provide immediate recognition of multiple stroke characters without using boxed input.

Abstract: A technology of the present invention is capable of objectively judging an ability of a proofreader who proofreads a digitized document by use OCR programs. A method of managing an ability of a proofreader who proofreads an electronic document generated from a recognition target document by executing a character auto recognition program, comprises a step of estimating a character count of potential mis-recognized characters contained in the electronic document, a step of detecting a mis-recognized character discover count as a mis-recognized character count with which the proofreader discovers the mis-recognized characters in the electronic document, a step of detecting a processing time spent for proofreading the electronic document, and a step of calculating a score relative to a proofreader ability based on a ratio of the potential mis-recognized character count to the mis-recognized character discover count per unit time.

Abstract: To enable a user to rapidly identify one or more sets of values for parameters of an operation, templates are generated dynamically from sets of values already used for these parameters in content available to the system. Each unique set of values may be extracted from the currently available content. Each of these sets of values may be sorted, for example, by recent modification date, for presentation to a user. The user may then select a set of values from among those displayed for use in the operation.

Abstract: The document scanner system and method operates in conjunction with a document imprinted with data in a plurality of data image fields and a plurality of form documents adapted to have data imprinted thereon. The system output to a communications port is a delimited string of decoded characters. The method scans to obtain positional information of data fields or accepts topological form input by the operator. The operator identifies data descriptors, e.g. field size, data type, etc. The system and method scans the document imprinted with data and captures an image thereof. The scanned input document image is compared with the stored forms (particularly the stored data field descriptors, e.g., positional information, and data type). The system selects a stored form, extracts the data from each field, decodes or calculates the data, and validates the data and stores the decoded/calculated data in the output sequence.

Abstract: The present invention relates to a method and apparatus for reading address fields on mail items when the address field cannot be automatically read. Herein, when an address field cannot be read, a signature of the surface of the mail piece where the address field is believed to be is made. The signature is derived from a scanning the surface and forming a grid pattern of the larger typographical fields. A database is queried to determine if a match exists between the signature and another signature. If a match is found, the information is imported into the automatic reading process, the information assisting in the reading of the address field. If no match is found, the scanned image is manually encoded and this information is used.

Abstract: A user-interface for selecting text from images of documents using auto-completion is described. The auto-completion process may be used to complete words (or text sequences), phrases, sentences, paragraphs, or other groupings of words. In response to user input, the OCR results for one or more images of documents are searched. The user input may include typing in a partial word (or the initial characters in a text sequence) via an input device or alternatively, annotations made by a user on a hardcopy document prior to scanning the document. One or more word matches are presented to the user for acceptance until the user accepts a word match or until all word matches have been presented to the user. Once a user accepts a word match, the word match is copied into an electronic document such as a word processing document, spreadsheet document, or other electronic document created by an application program.

Abstract: A method for data key-in includes receiving images of documents containing characters and receiving character codes entered by one or more key-in operators, the codes corresponding respectively to the characters in the documents. For at least some of the character codes, respective areas of the images that contain the corresponding characters are identified, such that each of the areas contains one of the characters. A group of the areas of the images is displayed together responsive to the corresponding character codes, so as to facilitate verification of the codes by a verifying operator.

Abstract: A method for displaying data includes receiving an input image of alphanumeric characters appearing on first and second lines. The characters are concatenated into a single line so as to generate an output image in which the characters from the second line follow the characters from the first line substantially without interruption therebetween, while maintaining a visual distinction between the characters from the first line and the characters from the second line.

Abstract: A method and apparatus for interactively and automatically enhancing image data by modifying one or more features of an image. The method includes inputting image data representing an image to be modified, analyzing the image for features to be modified, automatically selecting one or more feature to be modified, determining a first degree of modification using a automatic image enhancement techniques or a stored user preference, reversibly modifying the image based on the selected image feature and the first degree of modification, showing the image before improvement, showing the image after improvement and allowing the user to further modify at least one feature of the image data.

Abstract: A method carried out at a device (700), of limiting visual information that can be stored or transmitted captures a visual image (408). Whenever a control signal is detected (412) at the device (700), an optical symbol recognition of the image is performed. The method further includes comparing symbols generated by the optical symbol recognition routine to one or more predetermined symbols. When a symbol match to one or more predetermined symbols is generated, at least a portion of the visual image (408) is obscured.

Abstract: A document processing system comprises an input receptacle for receiving documents. A transport mechanism receives the documents from the input receptacle and transports the documents past a full image scanner and a discrimination unit. An output receptacle receives the documents from the transport mechanism after being transported past the full image scanner and the discrimination unit. The full image scanner includes means for obtaining a full video image of said documents, means for obtaining a image of a selected area of said documents, and means for obtaining information contained in said selected area of said document. The discrimination unit includes means for determining the authenticity of said document. A system controller directs the flows of documents over the transport mechanism.

Abstract: Composing image data representing an original image in an image processing device, the image processing device having an input device and a display device, including performing a block selection process on the image data to identify at least one image block and to determine a set of block attribute data for each identified image block, displaying a composite image on the display device, the composite image comprised of each identified image block superimposed on the original image, receiving a block designation command from the input device, the block designation command designating one of the identified image blocks as a designated image block, and displaying, in response to the block designation command, a function command list for the designated image block, the function command list containing a plurality of function commands based on the set of block attribute data for the designated image block.

Abstract: An imaging system includes two sets of cameras: a first set for capturing optical mark or optical character recognition data and a second set for capturing visual images. Full visual images of pages containing answers to open-ended questions are retained and are retrievable by a reader such that an area of interest wherein the answer is expected is displayed, but the remaining area is also available for viewing. The system permits the alignment of a page based upon edge detection if the page contains only an open-ended answer, obviating the need for timing tracks. Hardware and software elements cooperate to store the image temporarily in a server having a response time commensurate with the scanner. The image is then processed with the use of high-performance index imaging for optical storage and retrieval, and then routed to a long-term storage device.

Abstract: An improved method of deriving the correct text from text with errors converted from a character recognition device includes the need for significantly less human intervention for correction of the converted text.

Abstract: A method of deriving geometrical data of a structure from an image of the structure comprises the selection of marker points in the image. A typical contour is associated with the marker points and the geometrical data is calculated from the typical contour. According to the invention, correctness values are associated with the marker points. The correctness values indicate the reliability of the correspondence of the marker points to typical (anatomical) features in the structure. Furthermore, a cost function is associated with a typical contour, which cost function is dependent on the correctness values of the marker points. The typical contour is arranged in such a manner that the cost function reaches an optimum value, such as a local maximum or minimum value. The method is particularly suitable for deriving geometrical data, such as angles and distances concerning the spinal column of a patient.

Abstract: In an apparatus and method for creating a three-dimensional model of an object, images of the object taken from different, unknown positions are processed to identify the points in the images which correspond to the same point on the actual object (that is “matching” points), the matching points are used to determine the relative positions from which the images were taken, and the matching points and calculated positions are used to calculate points in a three-dimensional space representing points on the object. A number of different techniques are used to identify the matching points, and a number of solutions are calculated and tested for the relative positions, the solution which is consistent with the largest number of matching points being selected.

Abstract: The present invention provides a computer implemented method and apparatus for modifying data to be used by a client application in a client/server network. The steps for implementing the present invention include: transmitting information to the server computer from the client computer, wherein the transmitted information defines the intended use of data in a client application stored on the client computer; based on the transmitted information, modifying the data to optimize the data for its intended use by the client application, wherein such modification is performed by the server computer before transmitting the modified data to the client application. In the preferred embodiment, the modifications to the data are made as the request is made from the server application. The data modifications are performed by the server computer and are based on information about the client application's intended use of the data.

Abstract: A device is provided for capturing complete analog motion, rather than digital events. A beam of columnated light, generated from a laser emitting diode, it directed at a clear, rotatable ball bearing having a series of reflecting indicia within the surface of the ball bearing. The reflection of columnated light off of these indicia makes the analog motion of the ball bearing a capturable, optical event. A sensor reads through the clear ball bearing and converts this motion into memory. The raw data then goes into the temporary RAM, which holds all excess data as other date is streamed into the microprocessors. Those processors change the raw data into digital code, which can then be understood and translated by most modern personal computers. The digital code can then be stored in the unit's non-volatile RAM, where it remains until it is uploaded into a PC resident software program.

Abstract: A video image decoding and composing apparatus includes: a composing information memory for storing composition information; an arbitrary shape object decoding means for decoding a coded signal of an arbitrary shape object video image; a shape memory for storing a shape signal which is decoded by the arbitrary shape object decoding means; a texture memory for storing a texture signal which is decoded by the arbitrary shape object decoding means; a rectangular shape object decoding means for decoding a coded signal of a rectangular shape object video image; a video image memory for storing a video image signal which is decoded by the rectangular shape object decoding means; a composing means for composing the shape signal stored in the shape memory, the texture signal stored in the texture memory, and the video image signal stored in the video image memory, in accordance with the composition information stored in the composition information memory; a position indicating means for indicating a position in the c

Abstract: A system and method for providing user assistance to a user of a digital image device. The present invention, referred to as an interactive context assistant, includes computer-readable instructions stored in a memory unit of the digital image device which are executed by a central processing unit. The present invention is configured to automatically recognize an attribute of the image data. The present invention also includes a database which specifies the user assistance according to the attribute of the image data. The present invention retrieves from the database the user assistance corresponding to the attribute and provides the user assistance to the user via a user interface.

Abstract: A hand-writing input and recording device is housed in a case and may be hand-held by a user when in use. The device includes a contact element, an amplifying element, a sense element, an X-Y axes matrix element, a recording and storing element, a transmitting element and a receiving element. When the contact element generates a displacement variation in the X-Y axes, the X-Y axes displacement variation value will be emitted from the transmitting element to the receiving element and input into a computer for display on a computer screen to show the characters or patterns generated from the X-Y axes displacement variation value.

Abstract: A method for determining reproducibly if visual features of an object are known to a person. For that purpose, one or more test images are prepared by applying predetermined algorithms so that an image of the respective object is altered such that cognitive perception is in general impossible whereas the global affective impression is not influenced. The test images are presented to a person and it is determined if recognition occurs and if so how certain and how correct. Finally, it is determined which parts of the original images can be reproduced based on information recalled from the memory and if there is confusion or interchange with other images.

Abstract: The image processing apparatus includes a detection device which detects an improper image portion of image information, a correction device which corrects the improper image portion, a display device which displays an image whose improper image portion has been corrected by the correction device and an instruction device which instructs to re-correct the improper image portion using the image displayed on the display device.

Abstract: A method for data entry, includes receiving a plurality of images and sorting the images into an order responsive to a measure of similarity between the images, so as to group similar images together in the order. A first image among the images in the order is presented to an operator, and an input is received from the operator specifying a code to be assigned to the first image. A second image, subsequent to the first image among the images in the order, is then presented to the operator, along with the code specified by the operator for assignment to the first image. The code is assigned to the second image responsive to a single input action by the operator, indicating that the second image is to be assigned the same code as the first image.

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: A computer with a monitor viewable program executes to display a histogram of image data on the monitor. The monitor contemporaneously displays a screen image viewed on a monitor of the histogram, and displays a digital or analog control element that controls both compression and expansion of midtones. Activation of the midtone compression/expansion element alters the displayed image according to effects of programs underlying the control of the element. This histogram display and element are associated on a single logical screen display in which at least one other image data modification effect is present on the screen image as an addressable image data modification effect.

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: A data medium handling apparatus and a data medium handling method suitable for use for handling of documents, for example, in a financial organ. The data medium handling apparatus (30) for recognizing, based on an image (19) read from a data medium on which information is described in an arbitrary format, the information, is constructed such that it comprises means (2) for extracting characteristics unique to the data medium including the format from the read image data (19) and specifying, from the characteristics, a position at which information to be recognized is present, and image recognition means (3) for recognizing the image (19) at the position specified by the preceding means (2) to discriminate the information, so that the data medium handling apparatus (30) can handle documents having various formats such as private slips.

Abstract: A method for image processing includes analyzing one or more images so as to determine a respective classification for each of a multiplicity of elements in the images, wherein the elements are not individual characters in a language or numerical system. A plurality of the elements that have the same classification and were found at different locations in the one or more images are displayed together for a human operator. An input is received from the operator indicative of whether the computer erred in the classification of any of the displayed elements.

Abstract: A pen-based computer text input system capable of interpreting a special pre-defined set of single stroke glyphs. Each input stroke is identified with one of three categories: (1) pre-character modifier strokes, (2) character or symbol strokes, or (3) post-character modifier strokes. Pre-character modifier strokes precede character strokes and inform the present recognition system that a subsequently entered character stroke is to be modified by the pre-character modifier stroke in a pre-defined manner. Character strokes cause a character or symbol to be displayed on the display device the moment it is input on the writing tablet, interpreted in accordance with any pre-character modifier stroke. A post-character modifier stroke causes the recognition system to modify, in a pre-defined manner, a character or symbol which was previously entered and displayed. An important advantage of the present invention is its ability to provide immediate recognition of multiple stroke characters without using boxed input.

Abstract: A video processing device and method for generating a descriptor data structure representative of a feature that has been selected from among of plurality of features including visual, conceptual, textual and graphical of a visual animated data file includes a user input unit for selecting a desired feature and generating an associated descriptor data containing attribute values, and a processor identifies the selected feature inserts selected attribute values into a standard descriptor template. Various types of features, from concepts about a video sequence, to age identification, to images in a video clip, to particular objects or colors can all be classified in a standard descriptor template, to provide uniformity in storing and retrieving the various features currently lacking in freeform or single feature descriptors.

Abstract: A character image is inputted by use of a scanner, and recognized. The resultant character string of such recognition is represented on a display. The image serving as recognition source of the character designated on the display screen thereof, and the image in the vicinity of such image are represented. A character frame, which can discriminate the character image serving as recognition source, is edited in order to designate a new character image. This image and the inputted character information are registered on a character recognition dictionary correspondingly. Thereafter, the character recognition is carried out even with the utilization of such newly registered character. As a result, the recognition rate of the character recognition increases one after another.

Abstract: A document image that is the source of Optical Character Recognition (OCR) output is displayed. Recognition confidence parameters are determined for regions of the document image corresponding to words in the OCR output. The regions are displayed in a manner (e.g., highlighted in various colors) that is indicative of the respective recognition confidence parameter. Preferably, a user can select a region of the displayed document image. When the region is selected, text of the OCR output corresponding to the selected region is displayed in a pop-up menu.

Abstract: The present invention provides a system for making single, merged digital images including a processor configured to provide a digital image, a monitor configured to display the digital image, a user input device configured to accept commands from a user and software associated with the processor. The software is configured for providing at least one object cursor capable of receiving a selected portion of the digital image when overlaid on the digital image, wherein the software is also configured to merge the object cursor and selected portion of the digital image into a single image.

Abstract: A method and apparatus for erasing a feature from a digital image. The method includes identifying a plurality of tip regions on the image each including multiple pixels of the image and each covering a portion of the feature and sequentially processing the tip regions to erase the feature. The sequential processing includes determining an erasure color, defining a color match function for the tip region, applying the color match function to each pixel in the tip region including determining a color match value for each pixel and completely erasing ones of the pixels in the tip region that have a color match value greater than a threshold value. For a pixel having a color match value less than the threshold, an erasure function is applied to the target pixel. A contribution of the erasure color is removed from a color associated with the target pixel where the effect of each action of processing a tip region is recorded in the digital image before any subsequent action of processing a tip region is performed.

Abstract: A method is disclosed for automatically correcting an incorrectly recognized or converted character of text input onto a display screen of a computing device (e.g., a pen-based computer system such as a personal digital assistant) with a next most likely intended character upon actuation of a correction key. The next most likely intended character is preferably determined by ranking a plurality of potential intended characters, and then selecting a highest ranking character from the ranked plurality of potential intended characters as the next most likely intended character. The plurality of potential intended characters may be ranked based on statistical probabilities that one character will be incorrectly converted as another character, common sense that one character will be incorrectly converted as another character, and prior handwriting data choices collected for a user of the computing device.

Abstract: Composing image data representing an original image in an image processing device, the image processing device having an input device and a display device, including performing a block selection process on the image data to identify at least one image block and to determine a set of block attribute data for each identified image block, displaying a composite image on the display device, the composite image comprised of each identified image block superimposed on the original image, receiving a block designation command from the input device, the block designation command designating one of the identified image blocks as a designated image block, and displaying, in response to the block designation command, a function command list for the designated image block, the function command list containing a plurality of function commands based on the set of block attribute data for the designated image block.

Abstract: The present invention is to discriminate and extract a gesture stroke from a group of input strokes when inputting, in a batch processing, both a character or symbol of strokes to be processed and a gesture of strokes selecting a process to be executed for the character or symbol, and execute a process selected by the gesture stroke for all the strokes but the extracted gesture stroke, so that the character or symbol and the gesture do not need inputting individually at time intervals, thus improving the operability.

Abstract: A user interface high-lighter function for scanner software that allows a user to automatically select a portion or several disjoint portions of text within a region of text in a preview scan of a document. When activated, the high-lighter function causes the normal mouse cursor to be replaced with a high-lighter icon having an active edge. Using the mouse, the active edge of the high-lighter icon is moved across a desired portion of text, and background pixels traversed are displayed in a different color. The traversed pixels are then used as input for an image processing routine. Text regions are generated from the traversed pixels. The beginning and ending of lines not high-lighted are cropped. A polygonal bounding box is then displayed around the selected text. An un-highlight mode can be activated to reduce the selected text. An optimized re-scan of the to selected text can now be performed.

Abstract: Images at two or more correction levels are output as corrected images for a given image, and a user is allowed to select a preferred corrected image. Based on the selection result of the user, an image to be corrected which is different from the given image is corrected.

Abstract: Apparatus and method for improving recognition of patterns such as alphanumeric characters. A known recognition system is expanded to further include a complementary recognition system which is linked with the primary recognition system. An image that can not be positively recognized by the primary recognition system is passed on to the complementary recognition system and any characters not positively recognized by the complementary recognition are again passed on to a correction system. At the correction system, an operator classifies unrecognized characters which are then used to teach the complementary recognition system. Thus, the classified data of the correction system provide the training data for a continuous training process which is coupled with the correction system by a pattern adaptation system.

Abstract: A method and system for implementing an efficient alphanumeric text entry interface for a portable digital electronic device. A first entry area and a second entry area are generated for display on the incorporated display screen of a digital electronic device. The first and second areas are configured to display alphanumeric characters. A cursor is generated for selecting from among the various alphanumeric characters displayed in the first area and the second area. The cursor is operable to highlight a currently selected alphanumeric character such that the currently selected alphanumeric character is visible and easily distinguishable to the user. The movement of the cursor is controlled with the four way controller built into the digital electronic device. The four way controller is adapted for easy actuation by the user, wherein its movements are coordinated with the movement of the cursor on the display.

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: In a reduction process, data in portion buffers are selectively sampled at different sampling rates proportional to their assigned weights. For instance, portions assigned highest weights could be sampled at a reference rate corresponding to the repetition frequency of the originally received frames, portions assigned lowest weights could be sampled at {fraction (1/10)}th the reference rate, and portions assigned weights intermediate the lowest and highest ones could be sampled at rates less than the reference rate but more than {fraction (1/10)}th the reference rate. Accordingly, sampled portions assigned less than highest weights, but containing data representing objects in motion, could be subject to reproduction with less clarity than sampled portions assigned highest weight.

Abstract: A computer-implemented method and system for generating imprinted items customized by a user via the Internet or other interactive network. The method and system provides for receiving a specification of an item type, wherein associated with that item type are a plurality of constituent parts, including an image, which may be manipulated and edited. The method and system further provide for merging the item type data and constituent parts data to form a merged data set in a format suitable for a fabrication system. The fabrication system then incorporates the merged data with the selected item type to produce a finished product—an imprinted item customized by the user. The product is then provided to the user. Multiple products can be provided to multiple destinations.

Abstract: This invention discloses a key-in method including a manual keying in phase, and an automatic accuracy enhancement phase, wherein at least one of the manual phase, the automatic phase and the interaction therebetween is dependent, at least one dataflow point, on data generated previous to said dataflow point.

Abstract: A character reading system which reduces the amount of correction and verification work needed for a document for which characters have been correctly recognized. Whole image data WIMG of a document read by a remote OCR installed at a local station and first character data DATA1 recognized on the basis of a first character recognition method from this data WIMG are stored via a communication network in a memory component provided to a central station. A second recognition component provided to the central station recognizes second character data on the basis of a second character recognition method that is different from the first character recognition method from the image data WIMG read out from the memory component. A decision component decides whether there is a match between these first and second sets of character data. If there is a match, the data is outputted as correct character data, that is, third character data, to a host computer.

Abstract: In a method for recording a selected sequence of characters with the aid of a pen, the latter is passed over the sequence of characters and a plurality of images, whose contents partially overlap, are recorded simultaneously with the aid of a light-sensitive sensor (8) with a two-dimensional sensor surface. The recorded images are put together, horizontally as well as vertically, into an image. Subsequently, the characters in the composite image are identified and stored in the pen with the aid of a predetermined character code format. The putting-together, the character identification, and the storing are carried out with the aid of a signal processing unit (20-24). By the method and the pen compensation is obtained for different speeds of movement and different angles of rotation of the pen.

Abstract: In a postal information input apparatus in which when a postcode to be read by a reader of a postal matter sorting machine cannot be normally read, a correct postcode is reentered manually from an input device, a first display means which displays on a display device of the input apparatus a first display so as to indicate that the postal information input apparatus receives a data to be input from the postal matter sorting machine, and also displays an unprocessed number in the postal information input apparatus, is provided.

Abstract: A method and apparatus for determining the veracity of data. The method includes at least one comparison of manually input data and data generated by an automated process. The data generated by the automated process is typically the result of optical character recognition (OCR) and includes the generation of both classification of the optically read data as well as confidences for the data. For each piece of data processed by the OCR, the OCR program will generate a classification, which is a guess by the OCR program as to what that piece of data is, and a confidence level, which is the OCR's evaluation of how good the classification guess was. Depending on whether it is desired to check the accuracy of the manually input data or the results of the optical character recognition determines how the data is compared. The low confidence data is typically re-keyed into the system manually.