5231 results about "Character recognition" patented technology

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.

Ink strokes of cursive writing are segmented to make the cursive writing more like print writing, particularly with respect to the number of strokes of a character. A stroke-segmentation module first finds the local extrema points on a stroke of input ink. Then the local extrema points are stepped through, two (or three) at a time. The stroke-segmentation module may compare the three (or four) ink segments that are adjacent to the two (or three) local extrema points to a set of predefined stroke-segmentation patterns to find a closest matching pattern. Strokes are then segmented based on a stroke-segmentation rule that corresponds to the closest matching pattern. Additional stroke segmentation may be performed based on the change of curvature of the segmented ink strokes. Then, a character-recognition module performs character recognition processing by comparing the segmented ink strokes to prototype samples at least some of which have been similarly segmented.

The present invention features a playing card shuffling device, which through the use of a small image capturing means, captures an image of the face value of each card and stores the image in memory. This image is sorted in the format of a bitmap image. The operator of the machine would be able to recall through the use of a key pad, the images of the cards that comprised the individual hands in the previous game. This feature allows for verification of a winning hand after a game has been completed. Thereby, a quick recheck of hands before paying a winning hand is performed. The face value of each card is determined by character recognition software. These card values would be stored in memory for archival access for use in monitoring the randomness of the game and determining the number of winning hands.

A method for providing access to documents and data files that are inherently valuable, and also documents that contain sensitive information, is configured with robust user identification and document control capabilities and facilitates document submission by, for or on behalf of a user who perhaps is the subject of the document. The document is processed, optionally character recognized and steganographically marked, and is stored in a fixed format together with descriptive identifiers and database indexing values to facilitate control and searching. The level of security encourages users to entrust documents to storage and the system is programmed to control disclosure of documents (or parts of them) according to the user's dictates. Correspondingly strict user identification and document controls apply to those who log on for purposes of document review or serve as authenticators. The result is a virtual safe depository for documents that enables documents to be reviewed when necessary with reduced risk of misuse, for example by inadvertent disclosure to identity thieves and others.

A method for incremental recognition of ideographic handwriting comprises in order the steps of: (1) entering in a natural stroke order at least one stroke of an ideographic character from a computer entry tablet; (2) providing the at least one stroke to an incremental character recognizer, which produces a hypothesis list of at least one candidate character; (3) displaying a hypothesis list of candidate characters containing the at least one stroke; (4) selecting a correct character from among the candidate characters on the hypothesis list if it a correct character appears thereon; (5) entering in natural stroke order at least one additional stroke of the ideographic character from the computer entry tablet if no candidate character is a correct character; (6) providing the additional stroke(s) to the incremental character recognizer, which produces an updated hypothesis list; (7) displaying the updated hypothesis list of candidate characters containing every stroke; (8) selecting a correct character from among the candidate characters on the updated hypothesis list if it a correct character appears thereon; and (9) repeating steps (5) through (8) until a correct character is selected from the updated hypothesis list.

A digital writing system according to one embodiment of the present invention captures handwritten gestures in addition to text and patterns. It may include, among other things, a digital pen, special erasable ink and paper, and application software for the managing of captured files with a corresponding user interface. A digital pen according to one embodiment of the present invention may include character recognition subsystem, function control subsystem with selection mechanisms, a processor subsystem, memory subsystems, and wired or wireless communication subsystems. In addition, embodiments of a digital pen according to the present invention may include additional functional features including, for example, a user notification (e.g., alarm) feature, a digital camera feature, voice recording and recognition features, calendar features, calculator features, biometric sensor features, and the like.

The apparatus and method of the invention relate to data entry and menu selection. Applications include: (a) data entry for ideographic languages, including Chinese, Japanese and Korean; (b) fast food ordering; (c) correction of documents generated by optical character recognition; and (d) computer access and speech synthesis by persons temporarily or permanently lacking normal motor capabilities. In a preferred embodiment, each option of a menu is associated respectively with a selectable region displayed adjacent an edge of a display, forming a perimeter menu and leaving a region in the center of the perimeter menu for the output of an application program. Selectable regions may be on the display, outside the display, or both. A menu option may be selected by clicking on the associated selectable region, by dwelling on it for a selection threshold period or by a cursor path toward the selectable region, or by a combination thereof. Remaining dwell time required to select a selectable region is preferably indicated by the brightness of the selectable region. Submenus of a perimeter menu may also be perimeter menus and the location of a submenu option may be foretold by the appearance of its parent menu option. Menu options may be ideographs sharing a sound, a structure or another characteristic. Ideographs, which may be homophones of one another, may be associated with colored indicating regions and selection of an ideograph may be made by speaking the name of the associated color.

A phishing detection agent is provided. In one embodiment, a user's browser includes a plug-in application or agent that may capture a visual record of a webpage and, with a cached copy of known, authentic websites provided to it via periodic updates, perform a series of image comparison functions to determine if the suspected website is attempting to deceive the user. The phishing detection agent is capable of performing an image recognition algorithm, such as logo recognition algorithm, optical character recognition, an image similarity algorithm, or combination of two or more of the above. If the suspected webpage corresponds to one of the authentic web pages, but the domain name of the suspected web page does not match the domain name of one of the authentic web pages, the suspected web page is flagged as a phishing web site.

A method for incremental recognition of ideographic handwriting comprises in order the steps of: (1) entering in a natural stroke order at least one stroke of an ideographic character from a computer entry tablet; (2) providing the at least one stroke to an incremental character recognizer, which produces a hypothesis list of at least one candidate character; (3) displaying a hypothesis list of candidate characters containing the at least one stroke; (4) selecting a correct character from among the candidate characters on the hypothesis list if it a correct character appears thereon; (5) entering in natural stroke order at least one additional stroke of the ideographic character from the computer entry tablet if no candidate character is a correct character; (6) providing the additional stroke(s) to the incremental character recognizer, which produces an updated hypothesis list; (7) displaying the updated hypothesis list of candidate characters containing every stroke; (8) selecting a correct character from among the candidate characters on the updated hypothesis list if it a correct character appears thereon; and (9) repeating steps (5) through (8) until a correct character is selected from the updated hypothesis list.

A document image processing apparatus includes an image capturing unit for capturing an image of a document, a detecting unit for detecting focusing and twisting states of the capture image, a display unit for displaying the detected focusing and twisting states, a character recognition unit for recognizing characters written on the capture image, and a storing unit for storing the recognized characters by fields.

Embodiments herein provide / acquire a document in electronic form (e.g., by receiving, copying, retrieving from storage, scanning combined with optical character recognition, etc.) and receive user input regarding visual impairment. In response to one or more levels of user visual impairment, embodiments herein automatically change (for example, immediately after scanning text) an appearance of the document, without requiring any user input, other than the visual impairment input. More specifically, when changing the appearance of the document, embodiments herein can increase the size of characters in the document, change the contrast or coloring of the text and / or background, and provide text-to-speech conversion of the document, thereby (in one embodiment) producing audio output of the text-to-speech conversion in coordination with a corresponding portion of the document being displayed. When changing the appearance of the document, embodiments herein also reformat the document (e.g., around graphic elements) to accommodate the increased size of the characters.

A method of enabling remote deposit of checks includes receiving at a second site a plurality of check images and a plurality of entered dollar amounts, wherein the check images were generated at the depositor site by scanning the checks and the entered dollar amounts were manually entered at the depositor site. Each of the entered dollar amounts correspond to a respective one of the check images. The check dollar amounts are read from the check images at the second site using character recognition, and certain of the entered dollar amounts are used as hints to improve the accuracy of the character recognition. The enhanced character recognition results are provided to the depository bank along with the check images to enable the checks to be deposited in the depositor's account.

A financial transaction processing system for use at a point of presentment includes an input receptive of an image of a physical item at least partially embodying a financial transaction, wherein the image contains a visual record of an amount of monetary value. An image recognition module is adapted to extract the amount of monetary value recorded in the image and recognize the amount using character recognition. A validation module is adapted to determine whether the transaction is valid based on a validation characteristic of an item. A balancing module is adapted to determine whether the transaction is balanced based on the amount of monetary value. An output is adapted to transmit information indicating whether the transaction is at least one of balanced and valid.

An automated analysis method and tool for a digitally imaged financial item can digitally recognize a plurality of characters across an area of a digital image containing character indicia at predetermined positions in the area and also possibly containing non-character indicia in the area. This finds exemplification in an automated check processing method and check sorting system in which a check's MICR line that has been read and interpreted as invalid can be digitally analyzed, via a digital image of the check, to identify MICR characters that could not be validly read or interpreted by the conventional MICR processing equipment. This includes digitally applying character recognition processing to an invalidated MICR line in a digital image of the financial item (e.g., a check). Previously invalidated MICR line data can then be corrected.

A method for an intelligent identification system to recognize and validate currency base in the uniqueness of their numbers by employing video scanning apparatus in conjunction with optical character recognition (OCR) software and broadcasting capabilities so it can recognize the currency's value from a digitized serial number, store it with or without a “tag”, by memory means and be able to transmit and receive additional lists as a part of a network and as an extension; to recognize foreign countries currency, bank checks, personal checks and bills to be paid, for example: telephone bills, utility bills, etc.

Disclosed is a remote automatic meter reading (AMR) system for image-sensing, reading and transmitting metering values. The AMR system includes an AMR terminal, a collector and an AMR server. The AMR terminal includes an image sensing module for sensing an image signal of a metering value displayed on a display panel of the meter. A character recognition module performs pattern recognition of the image signal, and a communication module transmits digital data from the character recognition module to the AMR server side. The character recognition module may include a microcomputer and an ID setting During power saving mode, the microcomputer wakes up and decodes received data; and when a meter reading command is received, the image sensing module receives the image signal of the metering value, performs pattern recognition, generates the numeral code to form a packet together with the terminal ID, and transmits the packet to the communication module.

An embodiment of a method for splitting a bill includes displaying a primary bill that includes a plurality of items on a first payer device. A plurality of inputs are received from the first payer device that assign the plurality of items to a first payer and at least one second payer to generate a first secondary bill and at least one second secondary bill. Each at least one second secondary bill is then sent to a respective second payer device, and payments are sent for the first secondary bill from the first payer device and each at least one secondary bill from the respective second payer device. An image of a physical bill may be taken by the first payer device and optical character recognition may be performed on the image to produce the primary bill that is displayed on the display of a first payer device.

The invention discloses a plate number, body color and mark identification-based equipment and a plate number, body color and mark identification-based method for identifying fake plate vehicles. The equipment comprises a video detector, a plate number positioner, a plate number identifier, a body color identifier, a mark positioner, a mark identifier, a database query and alarm device and the like. According to the characteristic that the local edge information of the plate number image is rich, the equipment can accurately position a plate number in a captured image, extract a body region and a rough mark position by using the position of the plate number, and accurately extract a body color and a mark according to the extracted rough position; and then the equipment identifies the characters of the plate number, the body color and the mark, compares the results of the three identifications with data stored in a database to determine if a vehicle is a fake plate vehicle, and gives an automatic alarm for law enforcement officials to stop the vehicle for further check if the vehicle is a fake plate vehicle. The equipment is good in structure, simple in operation, high in judgment accuracy and few in manually set parameters. The equipment can also be used for catching escaped defaulting vehicles, stolen vehicles and peccancy vehicles and the like.

A system and method for collecting and managing information taken from tokens, like credit cards and gift cards, includes a portable computing device (PCD). The PCD may support a token recognizer that may comprise hardware and / or software that may reside in memory of the PCD. The token recognizer may work in combination with a camera. The token recognizer may comprise a broad recognizer module and an optical character recognition (“OCR”) module. The camera of the PCD may capture images of one or more physical tokens. These captured images of the physical tokens may be processed by the token recognizer so that digital images as well as data provided by the physical tokens may be maintained in memory of the PCD for later presentation to the user. These later presentations on the PCD may be used for account management and for conducting transactions, such as making payment at a point-of-sale (POS) terminal.

A memory circuit for an Aho-Corasick type character recognition automaton uses a node tree for recognizing predetermined strings of characters in an incoming data stream. The recognization is based upon successive transitions in the node tree stored in memory in which each node corresponds to a recognized sequence of a character string. At least part of the nodes are related to a consecutive node by a valid transition, from an initial state to terminal states, with each one corresponding to a recognized character string This memory circuit includes first sets of consecutive memory addresses defining respectively strings of consecutive nodes accessible sequentially during successive transitions to a terminal state, and second sets of memory addresses defining multiple nodes each pointing to several states.

The invention discloses a vehicle license plate character recognition method based on rough grid feature extraction and a BP neural network. The method comprises the following steps: (1). preprocessing a vehicle license plate image to eliminate various interferences and obtain a minimum vehicle license plate region; (2). segmenting the vehicle license plate characters by combining vertical projection and a drop-fall algorithm; (3). screening the segmentation results to eliminate interferences of vertical frames, separators, rivets and the like; (4). normalizing the characters according to the position of a centre of mass; (5). taking each pixel of a normalized characters dot-matrix as a grid to extract the original features of the characters; (6). designing the BP neural network with a secondary classifier according to the situation of the vehicle license plate; and (7). reasonably constructing a training sample database to train the neural network, and adjusting the training samples by the recognition effect to realize accurate recognition of the network. The method effectively eliminates the noise interference, quickly and accurately segments the characters, steadily and effectively recognizes Chinese characters, and realizes the balance between real-time property and accuracy in the whole recognition course.

A system and method are disclosed which provide a look-down digital imaging device capable of capturing relatively high resolution digital images (e.g., comparable to traditional flatbed scanners). A preferred embodiment provides a look-down digital imaging device comprising a linear sensor for imaging a raster line of an original image placed substantially below the look-down digital imaging device, and a lens for focusing reflected light from the original to such linear sensor. The linear sensor functions much as in traditional flatbed scanners in that it captures a single, congruent digital image of a scanned original. Most preferably, the linear sensor is a high resolution sensor that enables a digital image to be captured having resolution comparable to that of traditional flatbed scanners. For instance, the linear sensor preferably enables capture of a digital image having a resolution no less than approximately 300 dpi. As a result, such linear sensor most preferably captures a digital image having sufficient resolution to permit optical character recognition operations to be performed on such captured image. In a most preferred embodiment, the look-down digital imaging device further comprises a digital video camera for capturing video data of a target scan area. Such video data may be fed in substantially real-time to a display (either included within the look-down digital imaging device or included on a device to which the look-down digital imaging device is coupled), which may aid a user in properly aligning an original within the target scan area.

Methods for preventing unauthorized scripting. The invention generates a human interactive proof to distinguish a human from a machine by generating a random set of characters and altering each of the characters individually to inhibit computerized character recognition. The invention also includes concatenating the altered characters into a character string to be rendered to a user as a test. The character string may be altered to further inhibit computerized character recognition. Other aspects of the invention are directed to computer-readable media for use with the methods.

A system and method for computing confidence in an output of a text recognition system includes performing character recognition on an input text image with a text recognition system to generate a candidate string of characters. A first representation is generated, based on the candidate string of characters, and a second representation is generated based on the input text image. A confidence in the candidate string of characters is computed based on a computed similarity between the first and second representations in a common embedding space.

Accurately detection of logos in media content on media presentation devices is addressed. Logos and products are detected in media content produced in retail deployments using a camera. Logo recognition uses saliency analysis, segmentation techniques, and stroke analysis to segment likely logo regions. Logo recognition may suitably employ feature extraction, signature representation, and logo matching. These three approaches make use of neural network based classification and optical character recognition (OCR). One method for OCR recognizes individual characters then performs string matching. Another OCR method uses segment level character recognition with N-gram matching. Synthetic image generation for training of a neural net classifier and utilizing transfer learning features of neural networks are employed to support fast addition of new logos for recognition.

A process and system are provided for determining a most likely combination of characters. In particular, character data which includes information indicative of at least one handwritten character is obtained. The character data includes at least one set of segmentation points for the handwritten character. Then, a score can be provided for each particular character of a set of previously stored characters based on a comparison between the character data and the previously stored particular character. In addition, it is possible to compare visual aspects of the handwritten character to visual aspects of each of the previously stored characters for determining likely characters. Also, a Fisher Matching procedure can be used on the character data to ascertain the likely characters. A plurality of handwritten characters can include a first character that is connected to a second character of the handwritten characters via a ligature. A further score of the ligature can be determined based on a starting point of the ligature and an ending point of the ligature. Furthermore, the first character can be connected to the second character via a transition. A particular score of the transition can be ascertained based on a difference in length of the first character and the second character. This particular score can be combined with a score corresponding to the particular handwritten characters.

The invention relates to the field of image recognition, and especially relates to a complex character recognition method based on deep learning. Through the analysis of character complexity, a training sample, which contains a to-be-recognized image noise model and a distortion characteristic model, generated by a random sample generator is employed for the training of a deep neural network. The training sample comprises complex noise and distortion, and can meet the demands of the recognition of various types of complex characters. A few of manually annotated first training sample sets and a large amount of randomly generated second training sample sets are mixed and then inputted to the deep neural network, thereby solving a problem that a large number of manually annotated training samples are needed for character recognition through the deep neural network. Moreover, the most advanced deep neural network is employed for automatic learning under the condition that the noise and distortion of a to-be-recognized image are retained, thereby avoiding information loss caused by noise reduction in a conventional OCR method, and improving the recognition accuracy.