7780results about "Character recognition" patented technology

The invention is a method for omnidirectional recognition of recognizable characters in a captured two-dimensional image. An optical reader configured in accordance with the invention searches for pixel groupings in a starburst pattern, and subjects located pixel groupings to a preliminary edge crawling process which records the pixel position of the grouping's edge and records the count of edge pixels. If two similar-sized pixel groupings are located that are of sizes sufficient to potentially represent recognizable characters, then the reader launches “alignment rails” at pixel positions substantially parallel to a centerline connecting the center points of the two similarly sized groupings. A reader according to the invention searches for additional recognizable characters within the rail area, and subjects each located pixel grouping within the rail area to a shape-characterizing edge crawling process for developing data that characterizes the shape of a pixel grouping's edge. After adjusting the orientation representation of the shape-characterizing data the reader compares the developed shape-characterizing data to previously stored shape-characterizing data to determine the character represented by the grouping on the basis of the best fit data.

In accordance with some embodiments, a computer-implemented text selection method is performed using an electronic device having a touch-sensitive display. The method can include displaying text on the touch screen display; detecting a text selection initiation gesture with the touch screen display; and in response to the text selection initiation gesture, inserting a text selection area bounded by a first endpoint located in the text at a first location and a second endpoint in the text at a second location. First and second endpoints can be moved by performing further gestures on the touch-sensitive display. Furthermore, word processing functions can be performed on the on the text located in the text selection area.

The present invention provides a speech recognition system combined with one or more alternate input modalities to ensure efficient and accurate text input. The speech recognition system achieves less than perfect accuracy due to limited processing power, environmental noise, and / or natural variations in speaking style. The alternate input modalities use disambiguation or recognition engines to compensate for reduced keyboards, sloppy input, and / or natural variations in writing style. The ambiguity remaining in the speech recognition process is mostly orthogonal to the ambiguity inherent in the alternate input modality, such that the combination of the two modalities resolves the recognition errors efficiently and accurately. The invention is especially well suited for mobile devices with limited space for keyboards or touch-screen input.

A recognition object detecting portion detects a recognition object existing in each of images which are captured in series at different time points by a camera. Images of the detected recognition object are stored in a memory. A recognition object condition judging portion determines whether image areas of the recognition object are recognizable. A movement amount detecting portion detects a movement amount of the recognition object by using the image areas of the recognition object stored in the memory. A sub-area detecting portion detects a sub-area to be recognized, by using the image areas of the recognition object read out from the memory, in accordance with the movement amount of the recognition object. A recognition portion performs recognition processing on the sub-areas. A recognition result integration portion integrates recognition results of the sub-areas including recognized characters and / or recognized patterns and the corresponding reliabilities, respectively.

The present invention provides a speech recognition system combined with one or more alternate input modalities to ensure efficient and accurate text input. The speech recognition system achieves less than perfect accuracy due to limited processing power, environmental noise, and / or natural variations in speaking style. The alternate input modalities use disambiguation or recognition engines to compensate for reduced keyboards, sloppy input, and / or natural variations in writing style. The ambiguity remaining in the speech recognition process is mostly orthogonal to the ambiguity inherent in the alternate input modality, such that the combination of the two modalities resolves the recognition errors efficiently and accurately. The invention is especially well suited for mobile devices with limited space for keyboards or touch-screen input.

Systems and methods for virtual world simulations of the real-world or emulate real-life or real-life activities in virtual world or real life simulator or generating a virtual world based on real environment: host, at a server, a virtual world geography or environment that correspondences the real world geography or environment as a result, as the user continuously moves about or navigates in a range of coordinates in the real world, the user also continuously moves about in a range of coordinates in the real world map or virtual world; generate and access, by the server, a first avatar or representation, that is associated with a first user or entity in the virtual world; monitor, track and store, by the server, plurality types of data associated with user's real life or real life activities, actions, transactions, participated or participating events, current or past locations, checked-in places, participations, expressions, reactions, relations, connections, status, behaviours, sharing, communications, collaborations, interactions with various types of entities in the real world; receive, by the server, first data associated with a mobile device of the first user related to the first activity from the first geo-location co-ordinates or place; determine, by the server, one or more real world activities of the first user based on the first data; generate, record, simulate and update, by the server, virtual world based on said stored data, wherein updating a first avatar, that is associated with the first user or entity, in the virtual world; causing, by the server, a first avatar associated with the first user or entity, to engage in one or more virtual activities in the virtual world, that are at least one of the same as or sufficiently similar to or substantially similar to the determined one or more real world activities, by generating, recording, simulating, updating and displaying, by a simulation engine, simulation or a graphic user interface that presents a user a simulation of said real-life activities; and display in the virtual world, by the server, said real world activity or interacted entity or location or place or GPS co-ordinates related or associated or one or more types of user generated or provided or shared or identified contextual one or more types of contents, media, data and metadata from one or more sources including server, providers, contacts of user and users of network and external sources, databases, servers, networks, devices, websites and applications, wherein virtual world geography correspondences the real world geography. In an embodiment receiving from a user, a privacy settings, instructing to limit viewing of or sharing of said generated simulation of user's real world life or user's real world life activities to selected one or more contacts, followers, all or one or more criteria or filters specific users of network or make it as private.

A hybrid approach to improve handwriting recognition and voice recognition in data process systems is disclosed. In one embodiment, a front end is used to recognize strokes, characters and / or phonemes. The front end returns candidates with relative or absolute probabilities of matching to the input. Based on linguistic characteristics of the language, e.g. alphabetical or ideographic language for the words being entered, e.g. frequency of words and phrases being used, likely part of speech of the word entered, the morphology of the language, or the context in which the word is entered), a back end combines the candidates determined by the front end from inputs for words to match with known words and the probabilities of the use of such words in the current context.

A method and system are disclosed for conducting text-based searches of images using a visual signature associated with each image. A measure of string similarity between a query and an annotation associated with each entry in a first database is computed, and based upon the computed string similarity measures, a set of entries from the first database is selected. Each entry of the first database also includes an associated visual signature. At least one entry is then retrieved from a second database based upon a measure of visual similarity between a visual signature of each of the entries in the second database and the visual signatures of the entries in the selected set. Information corresponding to the retrieved entries from the second database is then generated.

An application on a mobile device provides for the initiation and submission of an insurance claim by capturing information and images of documents using an image capture capability, then processing the images to extract content which is transmitted to an insurance company for processing of the claim. Documents such as an automobile insurance card (AIC), driver's license, vehicle identification number (VIN), license plate, police report, damage estimate and repair invoice may all be captured and processed by image processing techniques on the mobile device or an image processing unit in order to extract relevant content. Other features and capabilities of the mobile device—such as video and image capture, location-based services, accelerometers and tracking—may automatically populate relevant fields of a claim report and permit the user to upload photographic and video evidence of an accident and related damage.

Defects such as dirt, dust, scratches, blemishes, pits, or defective elements or pixels in a CCD, scanner, photocopier, or image acquiring device are dynamically detected by processing a plurality of images via a computer. A pristine object of calibration is not required. Stationary components of the video images are found and detected so as to produce a low false alarm probability. Text segmentation and measurement of total deviation based on variability related to high-frequency components of the video image are employed to prevent applying the process or method to printed text or graphics. Additional techniques optionally employed are median filtering, sample area detection, and dynamic adjustment of scores. In special cases, only moderately blank documents are used. The dynamic defect detection allows defect compensation, defect correction, and alerting the operator of defects.

In a document processing apparatus, a first character information extracting unit extracts, for a first area that is an area determined to be a character extractable area in divided areas of a document information, first character information from the area; a second character information extracting unit extracts, for a second area that is an area not determined to be the character extractable area in the divided areas, a character code by performing a character recognition processing on a document image generated from the document information as second character information; and a storing unit stores therein the first character information, the second character information, and at least one of the document information and the document image in association with each other.

A deterministic finite automaton uses binary search (and optionally hashing) method(s) of sparse matrix representation to recognize the graphical representations of characters or icons from a bitmap representation of the computer screen. This recognition can be applied to translate data from an unknown form of original specification (file format) into a known form of representation, such as HTML. Alternatively this recognition can be applied to another process that can “see” what is on the screen, and perform programmed actions, based on what it “sees”.

A pure adversarial optical character recognition (OCR) approach in identifying text content in images. An image and a search term are input to a pure adversarial OCR module, which searches the image for presence of the search term. The image may be extracted from an email by an email processing engine. The OCR module may split the image into several character-blocks that each has a reasonable probability of containing a character (e.g., an ASCII character). The OCR module may form a sequence of blocks that represent a candidate match to the search term and calculate the similarity of the candidate sequence to the search term. The OCR module may be configured to output whether or not the search term is found in the image and, if applicable, the location of the search term in the image.

A character string is extracted from an image photographed by a camera. It is determined whether or not the extracted character string includes an address on a network. Software for accessing the address runs. Accordingly, a user can easily access a desired address on the network.

Systems and methods are provided for capturing and processing images of remittance coupons using a mobile device and obtaining data from the captured image which is used to set up or carry out payment of a bill that corresponds to the remittance coupon. Optimization and enhancement of image capture and image processing are provided on the mobile device to improve the initial quality of the captured image and provide a user with real time feedback. The image is then sent from the mobile device to a remote server, where additional image processing is performed to improve the quality of the image and then extract data from the image that is relevant to paying the bill. The extracted data may be verified through comparisons with databases which store information on billers, bill formats and other relevant content that will appear on the bill.

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.

A method and electronic device are provided for processing data. Analog text included in a document is detected. A first area of the analog text that converts to digital text and a second area of the analog text that does not convert to the digital text are determined. The digital text is displayed in the first area that converts to the digital text, and an image of at least a portion of the analog text is displayed in the second area that does not convert to digital text.

A method, computer program product, and a data processing system for scaling handwritten character input for performing handwriting recognition. A stroke parameter is derived from a handwritten character stroke and an input area is calculated in which the handwritten character stroke was supplied. The stroke parameter is scaled according to the input area.

A method of recognizing a handwritten word of cursive script comprising providing a template of previously classified words, and optically reading a handwritten word so as to form an image representation thereof comprising a bit map of pixels. The external pixel contour of the bit map is extracted and the vertical peak and minima pixel extrema on upper and lower zones respectively of this external contour are detected. Feature vectors of the vertical peak and minima pixel extrema are determined and compared to the template so as to generate a match between the handwritten word and a previously classified word. A method for classifying an image representation of a handwritten word of cursive script is also provided. Also provided is an apparatus for recognizing a handwritten word of cursive script. This apparatus comprises a template of previously classified words, a reader for optically reading a handwritten word, and a controller being linked thereto for generating a match between the handwritten word and the previously classified words. Two algorithms are provided for respectively correcting the skew and slant of a word image.

An apparatus and method for processing a captured image and, more particularly, for processing a captured image comprising a document. In one embodiment, an apparatus comprising a camera to capture documents is described. In another embodiment, a method for processing a captured image that includes a document comprises the steps of distinguishing an imaged document from its background, adjusting the captured image to reduce distortions created from use of a camera and properly orienting the document is described.

A method is disclosed for classifying an input pattern into an associated class through use of a compound classifier. Data pertaining to preselected features present within the input pattern are extracted. A discriminant value for each of a plurality of classes is then determined via a first classification technique. This value reflects the relative likelihood that a class is the associated class. The class with the highest relative likelihood is selected. A confidence value is generated via a second classification technique. This confidence value is reflective of the a posteriori probability that the selected class is the associated class. The selected class is rejected if the determined confidence value is below a predetermined threshold value.

Systems and methods are provided for capturing and processing images of remittance coupons using a mobile device and obtaining data from the captured image which is used to set up or carry out payment of a bill that corresponds to the remittance coupon. Optimization and enhancement of image capture and image processing are provided on the mobile device to improve the initial quality of the captured image and provide a user with real time feedback. The image is then sent from the mobile device to a remote server, where additional image processing is performed to improve the quality of the image and then extract data from the image that is relevant to paying the bill. The extracted data may be verified through comparisons with databases which store information on billers, bill formats and other relevant content that will appear on the bill.

A pen-enabled computing arrangement includes a handwriting capture interface and at least one processing element, such as in the form of a computing system and a digital pen that embodies a writing stylus. The handwriting capture interface can capture an electronic handwriting input. The processing element can sense an identifier associated with an object, and associate electronic handwriting input with the object. The processing element can then process the electronic handwriting input based upon the associated object. Printed paper with which the arrangement can operate to effectuate capturing and processing data may also be provided. Further, triggered verification of the sensed identifier may be provided when the identifier is sensed based upon initial electronic handwriting input corresponding to the identifier and the sensed identifier is unknown and / or improper.

A system and method for detecting cheque fraud includes a cheque scanning module and a detection module. The cheque scanning module scans cheques and matches the encoded Magnetic Ink Character Recognition (MICR) data (i.e. serial number, Customer Account Number and amount) from the scanned digital electronic images with items in an issuance database which contains client provided cheque particulars. The detection module passes the cheque images through an optical character recognition (OCR) process to read what is written on the cheque and to match results against the issuance database. If the written information on the face of a cheque is unreadable or there is no match with the information in the issuance database, the detection module passes the cheque through a series of slower more precise OCR processes. Any cheques that are not successfully read and matched are highlighted as an “exception” and immediately forwarded to the client for further action.

A method and apparatus are provided for analyzing an electronic communication containing imagery, e.g., to determine whether or not the electronic communication is a spam communication. In one embodiment, an inventive method includes detecting one or more regions of imagery in a received electronic communication and applying pre-processing techniques to locate regions (e.g., blocks or lines) of text in the imagery that may be distorted. The method then analyzes the regions of text to determine whether the content of the text indicates that the electronic communication is spam. In one embodiment, specialized extraction and rectification of embedded text followed by optical character recognition processing is applied to the regions of text to extract their content therefrom. In another embodiment, keyword recognition or shape-matching processing is applied to detect the presence or absence of spam-indicative words from the regions of text. In another embodiment, other attributes of extracted text regions, such as size, location, color and complexity are used to build evidence for or against the presence of spam.

A method automatically corrects dust artifact within images acquired by a system including a digital acquisition device including a lens assembly. Multiple original digital images are acquired with the digital acquisition device. Probabilities that certain pixels correspond to dust artifact regions within the images are determined based at least in part on a comparison of suspected dust artifact regions within two or more of the images. Probable dust artifact regions are associated with extracted parameter values relating to the lens assembly when the images were acquired. A statistical dust map is formed including mapped dust regions based on the determining and associating. Pixels corresponding to correlated dust artifact regions are corrected within further digitally-acquired images based on the associated statistical dust map.

A mixed media reality (MMR) system includes an MMR user, a MMR computer, a user printer that produces a printed document, a networked media server, an office portal, a service provider server, an electronic display that is electrically connected to a set-top box, a document scanner, a network, a capture device, a cellular infrastructure, wireless fidelity (Wi-Fi) technology, Bluetooth® technology, infrared (IR) technology, wired technology, and a geo location mechanism. The MMR system provides mechanisms for forming a mixed media document that includes media of at least two types, such as printed paper as a first medium and a digital photograph, digital movie, digital audio file, or web link as a second medium. Furthermore, the MMR system facilitates business methods that take advantage of the combination of a portable electronic device, voice mail or email, and a paper document.

An apparatus and method for processing a captured image and, more particularly, for processing a captured image comprising a document. In one embodiment, an apparatus comprising a camera to capture documents is described. In another embodiment, a method for processing a captured image that includes a document comprises the steps of distinguishing an imaged document from its background, adjusting the captured image to reduce distortions created from use of a camera and properly orienting the document is described.

Systems and methods are provided for capturing and processing images of remittance coupons using a mobile device and obtaining data from the captured image which is used to set up or carry out payment of a bill that corresponds to the remittance coupon. Optimization and enhancement of image capture and image processing are provided on the mobile device to improve the initial quality of the captured image and provide a user with real time feedback. The image is then sent from the mobile device to a remote server, where additional image processing is performed to improve the quality of the image and then extract data from the image that is relevant to paying the bill. The extracted data may be verified through comparisons with databases which store information on billers, bill formats and other relevant content that will appear on the bill.