Limited To Specially Coded, Human-readable Characters Patents (Class 382/182)
-
Patent number: 9367396Abstract: A method and system for service-aware parity placement in a storage system, including after receiving the service notification specifying a target SD: writing a RAID stripe to the persistent storage, where the parity block of the RAID stripe is stored on the target SD and none of the data blocks in the RAID stripe are stored on the target SD. The method further includes performing a modified garbage collection operation that includes identifying a live RAID stripe in the persistent storage, writing a new RAID stripe to a new location in the persistent storage, where the new RAID stripe includes a copy of at least a portion of data from the live RAID stripe and a parity block in the new RAID stripe is stored on the target SD, and issuing a removal notification when the modified garbage collection operation is completed.Type: GrantFiled: December 19, 2014Date of Patent: June 14, 2016Assignee: DSSD, Inc.Inventor: Jeffrey S. Bonwick
-
Patent number: 9342213Abstract: Provided is a mobile terminal including a display unit to which first screen information is output, a memory in which content included in the first screen information is selectively stored, and a controller that, when second screen information different from the first screen information is output to the display unit, controls the display unit in such a manner that the content associated with the second screen information among the items of content stored in the memory is output to one region of the display unit.Type: GrantFiled: October 28, 2013Date of Patent: May 17, 2016Assignee: LG ELECTRONICS INC.Inventors: Seulki Jung, Dongik Kim
-
Patent number: 9269009Abstract: Various embodiments enable a computing device to incorporate frame selection or preprocessing techniques into a text recognition pipeline in an attempt to improve text recognition accuracy in various environments and situations. For example, a mobile computing device can capture images of text using a first camera, such as a rear-facing camera, while capturing images of the environment or a user with a second camera, such as a front-facing camera. Based on the images captured of the environment or user, one or more image preprocessing parameters can be determined and applied to the captured images in an attempt to improve text recognition accuracy.Type: GrantFiled: May 20, 2014Date of Patent: February 23, 2016Assignee: AMAZON TECHNOLOGIES, INC.Inventors: Yue Liu, Sonjeev Jahagirdar, Matthew Joseph Cole, Utkarsh Prateek, Emilie Noelle McConville, Daniel Makoto Wilenson, Avnish Sikka
-
Patent number: 9251604Abstract: A method of generating a tomography image includes performing a depth scan on one spot on a surface of a subject using modulated light received from a spatial light modulator, obtaining depth scan data for each of a plurality of patterns of the spatial light modulator by repeating the depth scan on the spot for each of the plurality of patterns, forming a matrix R representing a vector space based on a correlation of signal values of the depth scan data for each of the plurality of patterns, performing a matrix decomposition on the matrix R, dividing the vector space into a noise subspace and a signal subspace based on a matrix obtained by the matrix decomposition, constructing a vector space based on either one or both of components of the signal subspace and components of the noise subspace, and generating a tomography image based on the reconstructed vector space.Type: GrantFiled: July 19, 2013Date of Patent: February 2, 2016Assignees: Samsung Electronics Co., Ltd., Korea Advanced Institute of Science and TechnologyInventors: Jae-guyn Lim, YongKeun Park, Jae-duck Jang, Seong-deok Lee, Woo-young Jang
-
Patent number: 9235779Abstract: An apparatus and a method for recognizing a character based on an input image is provided. The apparatus includes an input unit configured to receive the input image and a controller configured to select, from the input image, a region of image analysis to be used for image analysis, and to analyze the selected region of image analysis to determine a type of the input image, to apply, to the input image, an image effect for distinguishing a character region and a background region in the input image if the type of the input image indicates that the input image is obtained by photographing a display screen, to binarize output of the image effect according to the determined type of the input image, and to recognize a character from the binarized output of the image effect.Type: GrantFiled: June 12, 2015Date of Patent: January 12, 2016Assignee: Samsung Electronics Co., Ltd.Inventors: Sang-Ho Kim, Woo-Sung Kang, Mu-Sik Kwon, Jung-Rim Kim, Jeong-Wan Park
-
Patent number: 9176986Abstract: A server system receives a visual query from a client system distinct from the server system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query, and scores each textual character in the plurality of textual characters. The server system identifies, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query; retrieves a canonical document having the one or more high quality textual strings; generates a combination of the visual query and at least a portion of the canonical document; and sends the combination to the client system.Type: GrantFiled: December 1, 2011Date of Patent: November 3, 2015Assignee: Google Inc.Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Patent number: 9171205Abstract: A binarization device for payment or accounting documents including sensitive data located in respective data window provides a primary binarized document file of the document; a memory stores identification files including identifying images and location information associated to given types of documents; the data window can be identified and localized as comparison with the identification files of the memory; the contribution of the background is subtracted from the window file, the window file is binarized and filtered for spurious pixels obtaining a binarized window file; the binarized document file and the binarized window file are merged to provide the binarized window file in the data window; the evidence of the significant pixel is obtained by sequential analysis on groups of pixels, applying morphological expansion operators on each group of pixels and following erosion of said group of pixels.Type: GrantFiled: December 30, 2013Date of Patent: October 27, 2015Assignee: CTS ELECTRONICS S.P.A.Inventors: Barbara Penna, Patrizia Ugo
-
Patent number: 9171207Abstract: A method and system for recognizing machine generated character glyphs in a graphic image that uses a deterministic finite automaton (DFA) to separately recognize the individual pixelcolumns of character glyphs and then combines these separate pixelcolumns together to form correctly recognized whole glyphs. This method and system can enable data to be automatically exchanged between applications where no alternative method of data interchange exists. The DFA minimizes its space requirements by storing the current input dimension of its state transition table as a sorted list of possible values that could be matched at the current state. This sorted list can then be binary searched for the current input pixel RGB value.Type: GrantFiled: March 11, 2014Date of Patent: October 27, 2015Inventor: Peter L Olcott
-
Patent number: 9141899Abstract: A method for marking an article with an identification pattern which may include information relating to the article and/or to the use thereof, the method including: defining an alphabet of a plurality of symbols; defining, for each symbol, at least two valid states and at least one invalid state; developing a reference pattern including a set of symbols from the alphabet; developing at least one representation of the reference pattern by allocating a specific valid state to each symbol of the reference pattern; and applying a marking, reproducing the representation of the reference pattern, onto the article.Type: GrantFiled: September 24, 2010Date of Patent: September 22, 2015Assignee: SICPA HOLDINGS SAInventors: Eric Decoux, Dave Vuistiner
-
Patent number: 9082039Abstract: An apparatus and method for recognizing a character based on a photographed image. The apparatus includes an image determining unit, an image effect unit, a binarizing unit and a character recognizing unit. The image determining unit is configured to select, from an input image, a Region Of Interest (ROI) to be used for image analysis when the input image is input, and to analyze the selected ROI to determine a type of the input image. The image effect unit is configured to apply to the input image, an image effect for distinguishing a character region and a background region in a display screen if the type of the input image indicates that the input image is obtained by photographing a display screen. The binarizing unit is configured to binarize the input image or the output of the image effect unit according to the determined type of the input image. The character recognizing unit is configured to recognize a character from the binarized input image.Type: GrantFiled: December 12, 2012Date of Patent: July 14, 2015Assignee: Samsung Electronics Co., LtdInventors: Sang-Ho Kim, Woo-Sung Kang, Mu-Sik Kwon, Jung-Rim Kim, Jeong-Wan Park
-
Publication number: 20150146983Abstract: An image processing system comprises a generating unit that reads documents and generates a read image including document images; an extracting unit that extracts each of the document images; a character recognizing unit that performs character recognition processing on each the document images; a determining unit that determines whether first information and second information have a pair relationship, the first information being any one of recognition results obtained on one side of the document images, and the second information being any one of recognition results obtained on the other side of the document images; and a registering unit that registers pieces of information for the recognition results corresponding to the one side and to the other side respectively including the first information and the second information which are determined that both pieces of information have the pair relationship, as information for a piece of the documents, in a storage unit.Type: ApplicationFiled: November 14, 2014Publication date: May 28, 2015Inventor: Yoshihiko SAKAWAKI
-
Publication number: 20150146984Abstract: A system and method of for describing target data as a sequence of pattern elements and pattern element groups that comprise an overall target pattern is described. Pattern elements may utilize regular expression syntax along with other metadata that describe the behavior of the element. A pattern element group may be a collection of fully defined pattern elements where at least one pattern element from the group must have a match for the overall pattern to match. Patterns contain both pattern elements and pattern element groups. The general process involves first performing optical character recognition (OCR) on the document, which in turn produces a sequence of text tokens representing the lines of text on each page of the document. The search algorithm may then apply each defined pattern to the entire document capturing and/or extracting data that match each pattern's required elements and element groups.Type: ApplicationFiled: November 24, 2014Publication date: May 28, 2015Inventor: Jason Brown
-
Publication number: 20150146985Abstract: According to one embodiment, a handwritten document processing apparatus is provided with a stroke acquisition unit, a stroke group generation unit and an additional information generation unit. The stroke acquisition unit acquires stroke data. The stroke group generation unit generates stroke groups each including one or a plurality of strokes, which satisfy a predetermined criterion, based on the stroke data. The additional information generation unit generates additional information which indicates a relationship between a first stroke group of the stroke groups and a second stroke group of the stroke groups, and to assign the additional information to the first stroke group.Type: ApplicationFiled: February 6, 2015Publication date: May 28, 2015Inventors: Toshiaki Nakasu, Shihomi Takahashi, Tomoyuki Shibata, Kazunori Imoto, Yasunobu Yamauchi, Yojiro Tonouchi
-
Publication number: 20150139559Abstract: A system and method of processing an image of a document using an optical character recognition process is disclosed. In one example, the method comprises acts of extracting, by a computer system, a plurality of recognizable units from the document, extracting, by the computer system, a plurality of features from the plurality of recognizable units, separating, by the computer system, the plurality of recognizable units, based on the plurality of extracted features into a plurality of fragments having at least one fragment type, determining a distance metric between the plurality of recognizable units, based on the plurality of extracted features, and classifying, by the computer system, the plurality of recognizable units into a plurality of clusters based on the distance metric, each cluster including a set of recognizable units associated with a shape classification.Type: ApplicationFiled: September 14, 2012Publication date: May 21, 2015Applicant: GOOGLE INC.Inventor: Raymond Wensley Smith
-
Patent number: 9036923Abstract: Provided are an age estimation apparatus, an age estimation method, and an age estimation program capable of obtaining a recognition result closely matching the result perceived by human. An age estimation apparatus 10 for estimating an age of a person on image data includes a dimension compressor 11 for applying dimension compression to the image data to output low dimensional data; and an identification device 12 for estimating an age of a person on the basis of a learning result using a feature amount contained in the low dimensional data, wherein a parameter used for the dimension compression by the dimension compressor 11 and the feature amount used for age estimation by the identification device 12 are set on the basis of a result of an evaluation of a generalization capability using a weighting function that shows a degree of seriousness of an age estimation error for every age, and learning of the identification device 12 is performed on the basis of the weighting function.Type: GrantFiled: April 14, 2010Date of Patent: May 19, 2015Assignees: NEC Solution Innovators, Ltd., TOKYO INSTITUTE OF TECHNOLOGYInventors: Kazuya Ueki, Masashi Sugiyama, Yasuyuki Ihara
-
Patent number: 9036894Abstract: In a method and apparatus for identifying an embossed character, light of one color is directed in one direction across the embossed character to illuminate certain character parts and light of another color is directed in another direction across the embossed character to illuminate other character parts. Image data for the two colors are captured and are subjected to separate image processing to detect edges highlighted by the directed light. The processed images are combined and supplemented with OCR analysis before being compared with predicted characters. Based on the comparison, a determination is made as to the probable identity of the character.Type: GrantFiled: November 4, 2013Date of Patent: May 19, 2015Assignee: MEDAVAIL, INC.Inventor: Richard Panetta
-
Publication number: 20150131908Abstract: A character recognition method may include at least the following steps. A location step may include acquiring an image and locating a character region of the image. The character region may include a character and a local background. The method may further include a background judgment step for determining whether the local background is a complex background; a determination step for determining a color of the character if the local background is a complex background; a construction step for constructing a mask for the character by combining the color of the character and a character region; and a first recognition step for extracting the character from the character region by using the mask, recognizing the character, and outputting the recognition result. A character recognition device is further provided.Type: ApplicationFiled: January 23, 2015Publication date: May 14, 2015Inventors: Shuqi Mei, Yongjun Chen, Boxing Liu
-
Patent number: 9025877Abstract: A system and method using a text extraction application for identifying words with multiple orientations from an image are described. The text extraction application receives an input image, generates progressively blurred images, detects blobs in the blurred images, outputs ellipses over the blobs, detects a word in the input image, orients and normalizes a first version of the word, generates an inverted version of the word, performs OCR on the first version and the inverted version of the word, generates confidence scores for the first version and the inverted version of the word and outputs text associated with the word.Type: GrantFiled: January 4, 2013Date of Patent: May 5, 2015Assignee: Ricoh Company, Ltd.Inventors: Sri-Kaushik Pavani, Ekta Prashnani
-
Publication number: 20150117781Abstract: Methods, apparatus, and systems for information identification are provided. A card image of a pre-set collection area is photographed and obtained, when a request event for information identification is detected. Edge-size information of the card image obtained by photographing is determined. A target area of the card image is marked according to the edge-size information. An image of the target area is extracted. Character shapes to be identified in the image of the target area is determined based on a pre-set character pattern library. A character corresponding to each character shape to be identified is identified according to each character shape to be identified that is determined and according to the character pattern library.Type: ApplicationFiled: August 4, 2014Publication date: April 30, 2015Inventor: MAOCAI LI
-
Publication number: 20150117780Abstract: The invention provides a method of using machine vision to recognize text and symbols, and more particularly traffic signs.Type: ApplicationFiled: July 8, 2014Publication date: April 30, 2015Inventor: Victor Erukhimov
-
Patent number: 9020265Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: GrantFiled: June 5, 2014Date of Patent: April 28, 2015Assignee: Google Inc.Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong Man Cheung, Andrea Frome, Shlomo Urbach
-
Publication number: 20150110401Abstract: A document registration apparatus includes a receiving unit that receives a request for registration of a registration candidate document from a new registrant, a word extracting unit that extracts a word from the registration candidate document, a registrant information acquiring unit that acquires information on the new registrant, an associating unit that associates the extracted word with a group to which the new registrant belongs, a first storage unit that stores history information, a second storage unit that stores an identifier of a previous registrant and a group to which the previous registrant has belonged, an extracting unit that extracts an identifier of a previous registrant who registered a word identical to the extracted word, and extracts a group to which the previous registrant has belonged, a registration permission determining unit that determines whether to allow registration, and a document registering unit that registers the registration candidate document.Type: ApplicationFiled: June 16, 2014Publication date: April 23, 2015Applicant: FUJI XEROX CO., LTD.Inventor: Kazuya TANAKA
-
Patent number: 9008430Abstract: An identification method and apparatus of confusable character are provided. The method involves: the detected character image is identified to gain the initial character information which is corresponding to the character image; the step change times of the corresponding external outline of the character image are counted if the initial character information is the confusable character; the final character information corresponding to the character image is confirmed according to the step change times; The final character information of the character image can be known conveniently according to the step change times, therefore the corresponding correct character information of the character image can be identified more precisely. The possibility of wrong identification of the character image because of the appearing confusable character can be reduced, and the identification precision rate of the confusable character can be improved.Type: GrantFiled: December 27, 2010Date of Patent: April 14, 2015Assignee: Hisense TransTech Co., Ltd.Inventors: Nannan Wei, Weiqiang Chen, Xin Liu, Wei Liu, Lei Pei, Xiaoman Wang
-
Patent number: 9008428Abstract: Machines, systems and methods for character recognition disambiguation are provided. The method comprises selecting a first set of characters that match a first visual profile based on results of a character recognition process applied to target content; selecting a subset of the first set based on criteria associated with at least one of confidence level with which characters grouped in the subset are recognized or fragmentation associated with the characters grouped in the subset; and disambiguating recognition results for the characters grouped in the subset by displaying the characters along with context information, wherein reviewing two or more of the characters on a display screen along with context information associated with said two or more characters allows a human operator to select one or more suspect characters from among the two or more characters.Type: GrantFiled: January 28, 2013Date of Patent: April 14, 2015Assignee: International Business Machines CorporationInventors: Ella Barkan, Itoko Toshinari, Asaf Tzadok
-
Patent number: 9008431Abstract: In a character string extraction method, a character portion, a rim portion, a character frame, and a character string frame are set, a feature value of each image in the character portion and the rim portion is calculated for each character frame, a character string frame evaluation value is calculated based on the feature value for the character string frame, a position of the character string frame is moved on the paper sheet image, and the image in the character portion is extracted by using the character string frame at a position at which the character string frame evaluation value reaches a maximum.Type: GrantFiled: March 4, 2011Date of Patent: April 14, 2015Assignee: Glory Ltd.Inventors: Masanori Goto, Toru Yonezawa, Motoko Kuroiwa
-
Patent number: 9008429Abstract: A system and method for comparing a text image and a character string are provided. The method includes embedding a character string into a vectorial space by extracting a set of features from the character string and generating a character string representation based on the extracted features, such as a spatial pyramid bag of characters (SPBOC) representation. A text image is embedded into a vectorial space by extracting a set of features from the text image and generating a text image representation based on the text image extracted features. A compatibility between the text image representation and the character string representation is computed, which includes computing a function of the text image representation and character string representation.Type: GrantFiled: February 1, 2013Date of Patent: April 14, 2015Assignee: Xerox CorporationInventors: Jose Antonio Rodriguez-Serrano, Florent C. Perronnin
-
Patent number: 9002111Abstract: An image scaling service includes determining an image as a candidate for a scaling process, scanning the image for an initial text value, and scaling the image to a next lower resolution. The image scaling service also includes iteratively performing the scaling process until a threshold value of a readability metric is reached, the scaling process includes scanning the scaled image for a scaled text value, comparing a difference between the initial text value and the scaled text value, the difference indicative of the readability metric, and scaling the scaled image to a next lower resolution. In response to reaching the threshold value of the readability metric, the image scaling service further includes selecting from scaled images an image having a lowest resolution resulting from the scaling process before the threshold value of the readability metric was reached.Type: GrantFiled: April 16, 2012Date of Patent: April 7, 2015Assignee: International Business Machines CorporationInventors: William Bodin, Indiver N. Dwivedi, David Jaramillo
-
Patent number: 8995768Abstract: A method for processing data of a scanned book having a plurality of pages is disclosed. The method includes obtaining page image data from a page. The method further includes segmenting and recognizing the page image data to obtain locations of rectangular boxes corresponding to the respective characters and text codes for the respective characters. The method also includes obtaining respective aggregated character line information for each line of characters. The method further includes adjusting the rectangular boxes in accordance with the obtained aggregated character line information.Type: GrantFiled: December 28, 2012Date of Patent: March 31, 2015Assignees: Peking University Founder Group Co., Ltd., Beijing Founder Apabi Technology Ltd.Inventors: Ruiheng Qiu, Yun Li
-
Patent number: 8988318Abstract: A communication system and method are described for transmitting data from a display in a bit transmission data format to a machine vision system. The described system and method allows for the process and further application of a larger amount of data faster and more reliably than by use of the human readable data from the display. A standard LCD screen displays bit transmission data corresponding to human readable data, and transmits the bit transmission data to a machine vision system, such as by use of the camera on a smart phone. The captured bit transmission data is converted into a bit data stream for further processing, such as by use of an application in the smart phone, and can be stored in memory and/or transmitted to another system to provide useful human readable information. Faster transmission of a greater amount of data is realized including, in one aspect of the bit generation, data error and correction codes.Type: GrantFiled: July 29, 2011Date of Patent: March 24, 2015Assignee: Design Manufacture DistributionInventor: Christopher Chupp
-
Patent number: 8988543Abstract: The present invention relates to a camera based method for text input and detection of a keyword or of a text-part within page or a screen comprising the steps of: directing a camera module on the printed page and capturing an image thereof; digital image filtering of the captured image; detection of word blocks contained in the image, each word block containing most likely a recognizable word; performing OCR within each word block; determination of A-blocks among the word blocks according to a keyword probability determination rule, wherein each of the A-blocks contains most likely the keyword; assignment of an attribute to each A-block; indication of the A-blocks in the display by a frame or the like for a further selection of the keyword; further selection of the A-block containing the keyword based on the displayed attribute of the keyword; forwarding the text content as text input to an application.Type: GrantFiled: April 28, 2011Date of Patent: March 24, 2015Assignee: Nuance Communications, Inc.Inventors: Cüneyt Göktekin, Oliver Tenchio
-
Patent number: 8983211Abstract: A method, a system, and a computer program product for processing the output of an OCR are disclosed. The system receives a first character sequence from the OCR. A first set of characters from the first character sequence are converted to a corresponding second set of characters to generate a second character sequence based on a look-up table and language scores.Type: GrantFiled: May 14, 2012Date of Patent: March 17, 2015Assignee: Xerox CorporationInventors: Sriram Venkatapathy, Nicola Cancedda
-
Patent number: 8983191Abstract: One embodiment described herein may take the form of a system or method for dynamically recognizing an Internet address within a video or audio component of a multimedia presentation on a distribution system or network such as, but not limited to, a satellite, cable or Internet network. In general, the embodiment may analyze the audio portion of the presentation or one or more frames of a video component to detect the presence of a web address within the one or more frames. In the embodiment where the audio portion is analyzed, the system may perform a voice recognition or a similar analysis on the audio portion to detect the utterance of a web address. Similarly, one embodiment analyzing the one or more frames of the video component may comprise performing an optical character recognition (OCR) of the frame.Type: GrantFiled: October 18, 2010Date of Patent: March 17, 2015Assignee: EchoStar UK Holdings LimitedInventors: David John Robinson, Craig Avison-Fell
-
Patent number: 8983190Abstract: Dynamically configuring OCR processing may include determining a device type and determining whether to perform optical character recognition (OCR) processing of the received image locally based on one or more OCR parameters. Example OCR parameters may include the device type, the image type, the size of the received image, the available amount of the memory, the measured/benchmarked throughput of OCR processing on the device relative to an OCR server throughput and network throughput, and/or the current level of network connectivity. If it is determined that OCR processing of the received image should be performed locally, the device may compute one or more name-value pairs corresponding to the received image and transmit the name-value pairs to a remote data server for processing.Type: GrantFiled: August 13, 2013Date of Patent: March 17, 2015Assignee: Bank of America CorporationInventors: Georgios Katsaros, Donald Werner Schoppe, Bryan Anthony VonCannon, Pavan Chayanam
-
Patent number: 8977072Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.Type: GrantFiled: December 13, 2012Date of Patent: March 10, 2015Assignee: A9.com, Inc.Inventors: Raghavan Manmatha, Mark A. Ruzon
-
Patent number: 8977057Abstract: A system and method of assigning diacritics in an electronic image using optical character recognition (OCR) is disclosed. In one example, the method comprises analyzing, by a computer system, the electronic image to generate a plurality of bounding blocks associated with text lines within the electronic image. The method further comprises establishing a plurality of bounding boxes for diacritics and base text with the electronic image. The method also comprises determining a distance from a diacritic to a nearest base text character and a nearest text line. The method also comprises evaluating a base box distance and the nearest text line distance to assign the diacritic to a correct text line in the electronic image.Type: GrantFiled: November 9, 2012Date of Patent: March 10, 2015Assignee: Google Inc.Inventor: Raymond Wensley Smith
-
Patent number: 8976222Abstract: An image processing apparatus includes an image processing command input section to receive image processing commands for image data written into a memory by units of one line, a line number deriving section to derive a number of lines of the image data required to execute image processing operations based on the image processing commands received by the image processing command input section, a line number indicating section to output a numerical value indicating the number of lines of the image data derived by the line number deriving section, a read timing controlling section to control read timing from the memory in response to the numerical value output from the line number indicating section, a parameter indicating section to output parameters used for the image processing operations, and an image processing section to execute the image processing operations.Type: GrantFiled: December 17, 2012Date of Patent: March 10, 2015Assignee: Ricoh Company, Ltd.Inventors: Yohsuke Kawamura, Kohji Oshikiri
-
Publication number: 20150063700Abstract: Embodiments disclosed pertain to Optical Character Recognition using Multiple Hypothesis Testing based techniques on images occurring in a variety of settings, including images captured by mobile stations. In some embodiments, a set of bifurcation points for a character cluster in an image may be determined. The character cluster may comprise non-uniformly spaced text or closely spaced text. A plurality of hypotheses may be determined for the character cluster, where each hypothesis is based on a subset of the bifurcation points and comprises a set of words generated from the character cluster. A plurality of scores corresponding to the plurality of hypotheses may be determined, where each score corresponds to a hypothesis, and a hypothesis may be selected from among the plurality of hypotheses based on a score associated with the selected hypothesis.Type: ApplicationFiled: May 2, 2014Publication date: March 5, 2015Applicant: QUALCOMM IncorporatedInventors: Rajiv SOUNDARARAJAN, Kishor Kumar BARMAN, Pawan Kumar BAHETI
-
Patent number: 8971630Abstract: Methods are described for determining an optimal path for creating a scheme for dividing a text line of Chinese, Japanese or Korean (CJK) characters into character cells prior to applying classifiers and recognizing characters. Gaps between characters are found as a window is moved down the text line. Finding gaps may involve finding 4-connected paths. A histogram is built based on distances from start of window to a respective gap. The window is moved to the end of each gap after each gap is found and distances measured. Process is repeated until window reaches the end of the text line and all gaps found. A linear division graph (LDG) is constructed according to detected gaps. Penalties for certain distances are applied. An optimum path is one with a minimal penalty sum and can be used as a scheme for dividing text lines into character cells.Type: GrantFiled: June 19, 2012Date of Patent: March 3, 2015Assignee: ABBYY Development LLCInventor: Yuri Chulinin
-
Publication number: 20150055867Abstract: Systems and methods for efficiently processing electronically stored information (ESI) are described. The systems and methods describe processing ESI in preparation for, or association with, litigation. The invention preserves the contextual relationships among documents when processing and indexing data, allowing for increased precision and recall during data analytics.Type: ApplicationFiled: November 4, 2014Publication date: February 26, 2015Inventors: Michael Wade, Robert Nelson
-
Patent number: 8965128Abstract: A code recognition method includes the following steps: a first code-image block is received. Wherein, several first codes are displayed on the first code-image block. The first code-image block is partitioned into several second code-image blocks. Wherein, each of the second code-image blocks displays a second code respectively. Each of the second codes is one of the first codes. Each of the second code-image blocks is recognized as several third codes corresponding to each of the second codes respectively. Some of the neighboring second code-image blocks are combined to form several third code-image blocks. Wherein, each of the third code-image blocks displays a first code set, which comprises some of the second codes. Each of the third code-image blocks is recognized as a second code set corresponding to each of the first code sets respectively. Wherein, each of the second code sets includes the codes selected from the third codes.Type: GrantFiled: December 17, 2010Date of Patent: February 24, 2015Assignee: Institute for Information IndustryInventors: Yi-Chong Zeng, Jing-Fung Chen
-
Publication number: 20150049948Abstract: A device and method for providing a visual cue for improved text imaging on a mobile device. The method includes determining a minimum text size for accurate optical character recognition (OCR) of an image captured by the mobile device, receiving an image stream of a printed substrate, and displaying the image stream and a visual cue superimposed onto the image stream, wherein the visual cue is indicative of the minimum text size. The method further includes capturing a digital image of the image stream, wherein the digital image does not include the visual cue. Additionally, the method further includes notifying a user of the mobile device when text displayed within the image stream is at least as large as the minimum text size.Type: ApplicationFiled: August 16, 2013Publication date: February 19, 2015Applicant: Xerox CorporationInventor: Raja Bala
-
Publication number: 20150049947Abstract: Dynamically configuring OCR processing may include determining a device type and determining whether to perform optical character recognition (OCR) processing of the received image locally based on one or more OCR parameters. Example OCR parameters may include the device type, the image type, the size of the received image, the available amount of the memory, the measured/benchmarked throughput of OCR processing on the device relative to an OCR server throughput and network throughput, and/or the current level of network connectivity. If it is determined that OCR processing of the received image should be performed locally, the device may compute one or more name-value pairs corresponding to the received image and transmit the name-value pairs to a remote data server for processing.Type: ApplicationFiled: August 13, 2013Publication date: February 19, 2015Applicant: Bank of America CorporationInventors: Georgios Katsaros, Donald Werner Schoppe, Bryan Anthony VonCannon, Pavan Chayanam
-
Publication number: 20150049949Abstract: A system and method to error correct extant electronic documents is disclosed. An electronic document may be rasterized to obtain a pixel representation of the electronic document (e.g., raster image). One or more optical character recognition (OCR) tasks may be performed on the raster image of the electronic document. Errors discovered by the OCR tasks may be corrected and a customized error corrected version of the electronic document may be created and stored. If the author of the electronic document is known, the raster image may be compared to a personalized tf*idf error dictionary associated with the author to determine known OCR errors specific to the author. The raster image may also be compared to a personalized electronic error dictionary associated with the author to determine known typographical errors specific to the author.Type: ApplicationFiled: April 29, 2012Publication date: February 19, 2015Inventors: Steven J Simske, Samson J. Liu
-
Patent number: 8958645Abstract: Systems and methods for summarizing a video assign frames in a video to at least one of two or more groups based on a topic, generate a respective first similitude measurement for the frames in a group relative to the other frames in the group based on a feature, rank the frames in a group relative to one or more other frames in the group based on the respective first similitude measurement of the respective frames, and select a frame from each group as a most-representative frame based on the respective rank of the frames in a group relative to the other frames in the group.Type: GrantFiled: April 19, 2012Date of Patent: February 17, 2015Assignee: Canon Kabushiki KaishaInventors: Juwei Lu, Bradley Denney
-
Publication number: 20150043823Abstract: Various embodiments of a method and system for capturing and utilizing item attributes are described. Various embodiments may include a mobile image capture apparatus, which may include a computer system configured to execute an image capture application. The image capture application may instruct an agent to capture an image of an item label. A data extraction component may be configured to process the images captured by the mobile image capture apparatus. For a given captured image, the data extraction component may in various embodiments be configured to perform OCR to determine one or more strings of characters from the image. The data extraction component may be further configured to determine whether one or more patterns match a determined string of characters. In response to the detection of a particular pattern matching a particular string of characters, the data extraction component may extract and store an attribute of the corresponding item.Type: ApplicationFiled: October 27, 2014Publication date: February 12, 2015Applicant: AMAZON TECHNOLOGIES, INC.Inventors: ANDREW SEAN TYRA, IAN D. CLARKSON
-
Publication number: 20150043822Abstract: A device to convey information to a user regarding clothing. The device receives data that specifies a clothing mode to use for processing an image, accesses a knowledge base to provide data to configure the computer program product for the clothing mode, the data including data specific to the clothing mode and receives an image or images of an article of clothing. The device processes the image or images to identify patterns in the image corresponding to items of clothing based on information obtained from the knowledge base.Type: ApplicationFiled: October 27, 2014Publication date: February 12, 2015Applicant: K-NFB Reading Technology, Inc.Inventors: Raymond C. Kurzweil, Paul Albrecht, Lucy Gibson
-
Publication number: 20150042882Abstract: A method of acquiring information about content includes the operations of receiving a video signal from an external apparatus connected to an image display apparatus, extracting an object included in an on screen display (OSD) image from an image that is produced using the video signal, and collecting the information about content by using the extracted object.Type: ApplicationFiled: August 5, 2014Publication date: February 12, 2015Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Gyu-tae PARK, Hak-sup SONG
-
Patent number: 8948513Abstract: Methods, systems, and apparatus, including computer program products, for identifying regions of interest in an image and identifying a barcode in a degraded image are provided. A region of interest is identified by pre-processing an image, generating a binary image based on a metric calculated on the pre-processed image, and analyzing regions of the image identified using connected components and other analysis. A barcode is identified by searching a population of barcodes, degrading ideal image intensity profiles of candidate barcodes, and comparing the degraded ideal image intensity profiles to an image intensity profile of the degraded image.Type: GrantFiled: January 27, 2009Date of Patent: February 3, 2015Assignee: Apple Inc.Inventors: Rudolph van der Merwe, Richard Eugene Crandall, Samuel Gordon Noble, Bertrand Serlet, Stanislav Kounitski
-
Publication number: 20150023599Abstract: Machines, systems and methods for enhanced optical character recognition are provided. In one embodiment, the method comprises identifying a sample character in a textual context to be optically recognized; comparing the sample character with a template character, wherein the sample character is scaled into a first grid and the template character is scaled into a second grid; identifying one or more pixels in the sample character within the first grid and one or more pixels in the template character in the second grid, wherein the one or more pixels are identified as belonging to a foreground category in the textual content, a foreground pixel having at least N gradients corresponding to edges of the foreground pixel that are juxtaposed to a neighbor pixel, wherein a contour foreground pixel has at least one gradient that is neighbored by a background pixel in the textual context.Type: ApplicationFiled: July 17, 2013Publication date: January 22, 2015Inventor: Amir Geva
-
Publication number: 20150023600Abstract: Embodiments of the present invention provide a system and method for authorizing the use of a biometric transaction card. Specifically, embodiments of the present invention provide a biometric card having a biometric sensor to determine whether the biometric information (fingerprint) is from human skin. In a typical embodiment, the cardholder approaches a magnetic reader with the card. The user places his/her finger on the SpO2 sensor of the card. The sensor estimates the SpO2 level. Card authorization is based, in part, on the estimated SpO2 level.Type: ApplicationFiled: August 27, 2014Publication date: January 22, 2015Inventor: Moon J. Kim