Optical (e.g., Ocr) Patents (Class 382/321)
  • Patent number: 10425568
    Abstract: A display device includes a first communication unit connected to one or more peripheral devices, a second communication unit that communicates with a remote controller, and a processor. If the processor is initialized in response to a power-on instruction through the second communication unit, the processor verifies whether a first peripheral device, which is selected as a source device that provides at least one source of video and audio signals, among the one or more peripheral devices is powered on within a first threshold time. If the first peripheral device is not powered on within the first threshold time, the processor transmits a power-on request for allowing the remote controller to power on the first peripheral device, to the remote controller through the second communication unit.
    Type: Grant
    Filed: July 19, 2017
    Date of Patent: September 24, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Ji Won Kim, Hyung Joon Kim, Surng Kyo Oh, Cheul Hee Hahm, Weon Seok Heo, Ji Hyun Bae, Hae Kwang Lee, Dong Ryun Seok
  • Patent number: 10296751
    Abstract: In response to a request to transmit a message from a sender to a recipient, risk values including low and high values are assigned to a content risk rating via comparing content of the message to content risk criteria, to a sender risk rating as a function of a sender identity, to a recipient risk rating as a function of a recipient identity, and to a dissemination reach rating of the message as a function of association to a security level of a message distribution channel. A total message risk score is determined from the content disclosure risk rating, sender risk rating, recipient risk rating and dissemination reach rating values. The message is transmitted from the sender to the recipient or if the total message risk score meets a high risk threshold value; otherwise, a mitigation action is applied to the message.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: May 21, 2019
    Assignee: International Business Machines Corporation
    Inventors: Michael K. Boudreau, Joseph N. Dellatorre
  • Patent number: 10277755
    Abstract: An electronic device includes an image reading section, a marker detection section, and a processing section. The marker detection section analyzes image data and detects a first marker portion indicated in the image data and a second marker portion indicated in the image data in a mode different from a mode of the first marker, and also extracts texts indicated in the first marker portion and the second marker portion. The processing section performs processing of transmitting the image data where the text indicated in the first marker portion is defined as a file name of the image data and the text indicated in the second marker portion is defined as a transmission address to which the image data is transmitted.
    Type: Grant
    Filed: February 6, 2017
    Date of Patent: April 30, 2019
    Assignee: KYOCERA Document Solutions Inc.
    Inventors: Sachiko Yoshimura, Akihiro Umenaga, Yumi Nakagoshi, Jr., Naoto Hanatani, Hironori Hayashi
  • Patent number: 10261306
    Abstract: A method for execution upon operation of a microscope or for depiction of an object, or a part thereof, imaged with the microscope includes depicting a proxy of the object on a display of the microscope or on a further display. At least one manipulation is performed on the proxy, or on the depiction of the proxy, using an input means. At least one depiction parameter for the depiction of the object or of the part of the object, or at least one microscope control parameter, is derived from the manipulation. The object or the part of the object is depicted in consideration of the derived depiction parameter or of the derived microscope control parameter.
    Type: Grant
    Filed: April 19, 2013
    Date of Patent: April 16, 2019
    Assignee: LEICA MICROSYSTEMS CMS GMBH
    Inventors: Frank Hecht, Frank Sieckmann
  • Patent number: 10147333
    Abstract: A system for interactive online instruction includes an instructional subscription website and video management system configured to process video recordings. The video recordings may include (i) student videos uploaded by a student and (ii) instructor videos providing feedback to said student videos. A method of interactive online instruction is also disclosed. The method includes the steps of providing prerecorded course materials on an instructional subscription website including video lessons accessible by subscribing students, and providing a video management system configured to process video recordings including (i) student videos submitted by a student and (ii) instructor videos providing feedback to said student videos.
    Type: Grant
    Filed: October 16, 2015
    Date of Patent: December 4, 2018
    Assignee: ArtistWorks, Inc.
    Inventor: David A. Butler
  • Patent number: 10102764
    Abstract: A system includes an image capture device and an assessment computing device. The image capture device is configured to capture an image of an object and a first score associated with the object on a first scale. The assessment computing device is configured to receive the image of the object and the first score from the image capture device, and to receive a second score on a second scale that is different from the first scale from a third party assessment source computing device. The assessment computing device is also configured to normalize the second score to a particular scale to provide a normalized second score, and to determine a level of mastery based at least partially on the first score and the normalized second score. The assessment computing device is configured to generate a user interface with information indicating the level of mastery.
    Type: Grant
    Filed: June 22, 2016
    Date of Patent: October 16, 2018
    Assignee: ALTSCHOOL, PBC
    Inventors: Sarah Katharine Berk, Michael Ashley Martin
  • Patent number: 10049310
    Abstract: Provided are techniques for image text analysis for identifying hidden text. An Optical Character Reader (OCR) is utilized to extract a text string from an image. Context within the image is analyzed. It is determined that the extracted text string is a partial text string based on the context. For a first radius level of a plurality of radius levels, a segmented sub-image is identified around the partial text string within the first radius level, an image search on the segmented sub-image is performed to identify a candidate text string, and, in response to determining that the candidate text string is a complete text string, the complete text string is provided for performing an action.
    Type: Grant
    Filed: August 30, 2016
    Date of Patent: August 14, 2018
    Assignee: International Business Machines Corporation
    Inventors: Alaa Abou Mahmoud, Paul R. Bastide, Fang Lu
  • Patent number: 9971456
    Abstract: A display device including a surface for viewing an image comprising a stack of layers configured to display the image. A processor is configured to include switchable detection modes. Each mode is preconfigured to detect an object on or near the surface based on a given sensitivity to light, and has a different sensitivity than other of the modes.
    Type: Grant
    Filed: September 19, 2016
    Date of Patent: May 15, 2018
    Assignee: Apple Inc.
    Inventors: Adiel Abileah, Willem den Boer
  • Patent number: 9946949
    Abstract: Methods are systems are provided that include obtaining a digital image from a digital photograph, such as may be taken by a digital camera or a camera phone. The digital image includes, for example, a URI or URL, which may be contained within a visible frame. A character recognition technique, such as an optical character recognition technique, may be used to recognize the URI or URL from the digital image. The URI or URL may be used to access a corresponding Web page. The character recognition technique may be applied on the digital camera or cell phone itself, or remotely.
    Type: Grant
    Filed: April 12, 2017
    Date of Patent: April 17, 2018
    Assignee: Excalibur IP, LLC
    Inventor: Jin Suk Park
  • Patent number: 9858251
    Abstract: System and method of automatically generating a user-editable document to save search results for efficient management and utilization by users. A book reading program according to the present disclosure can receive a user search request and automatically save the search results to a designated annotation document according to a predetermined layout. Through various editing functions provided by the book reading GUI, a user can advantageously edit the annotation document. The results may be book or other passages that contain a query term. In the document, the passage themselves can be edited and the user can add additional content by using text editing features.
    Type: Grant
    Filed: August 14, 2014
    Date of Patent: January 2, 2018
    Assignee: RAKUTEN KOBO INC.
    Inventor: Benjamin Landau
  • Patent number: 9766694
    Abstract: There are disclosed a mobile terminal and a controlling method thereof, which is able to simply input a real-time external image to an input field as data, specifically, such that a user may input a character or picture captured from the real-time image inputted from the outside via the camera and that the real time image maybe captured without switching a screen displaying the input field, so as to allow a user to intuitively recognize which input field an object provided in the image is inputted to.
    Type: Grant
    Filed: April 22, 2013
    Date of Patent: September 19, 2017
    Assignee: LG ELECTRONICS INC.
    Inventors: Sehyun Jung, Sesook Oh, Yoonseok Yang, Shinnyue Kang, Kyungjin Moon
  • Patent number: 9756209
    Abstract: A terminal and a close-up photography method using the same are disclosed. The terminal includes a transparent display unit having front and rear surfaces through which light passes, the transparent display unit having a set thickness, at least one camera module disposed on the transparent display unit, configured to acquire an image of a subject in a direction of penetrating the transparent display unit, and a controller configured to control the camera module.
    Type: Grant
    Filed: November 4, 2013
    Date of Patent: September 5, 2017
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Mihyang Kim, Jeonghun Kim, Kwangweon Park, Yoywang Im
  • Patent number: 9666618
    Abstract: A pixel array includes a plurality of pixel structures, with each pixel structure having a photo-sensitive element for generating charge in response to incident light; a charge conversion element; a first transfer gate and a second transfer gate connected in series between the photosensitive element and the charge conversion element or between the photosensitive element and a supply line; and an output stage. A first transfer gate control line is connected to the first transfer gates of a first sub-set of the pixel structures in the array; and a second transfer gate control line connected to the second transfer gates of a second sub-set of the pixel structures in the array. The first sub-set of pixel structures and second sub-set of pixel structures partially overlap, having at least one pixel structure in common between them.
    Type: Grant
    Filed: June 29, 2012
    Date of Patent: May 30, 2017
    Assignee: CMOSIS NV
    Inventor: Guy Meynants
  • Patent number: 9652680
    Abstract: Methods are systems are provided that include obtaining a digital image from a digital photograph, such as may be taken by a digital camera or a camera phone. The digital image includes, for example, a URI or URL, which may be contained within a visible frame. A character recognition technique, such as an optical character recognition technique, may be used to recognize the URI or URL from the digital image. The URI or URL may be used to access a corresponding Web page. The character recognition technique may be applied on the digital camera or cell phone itself, or remotely.
    Type: Grant
    Filed: May 22, 2015
    Date of Patent: May 16, 2017
    Inventor: Jin Suk Park
  • Patent number: 9646512
    Abstract: Disclosed are systems, methods and computer program products for automated teaching of languages. In one example, a method includes receiving a text content in a natural language; parsing the received text content into one or more sentences; determining a syntactic model of the each sentence; determining a frequency of occurrence for each syntactic model based on a number of sentences associated with each syntactic model in the text content; sorting the one or more syntactic models based on each respective frequency; and generating one or more language teaching exercises, wherein an exercise includes one or more sentences selected based on the frequency of associated syntactic model.
    Type: Grant
    Filed: October 24, 2014
    Date of Patent: May 9, 2017
    Assignee: Lingualeo, Inc.
    Inventors: Artur Dumchev, Aynur Abdulnasyrov, Grigory Glushko
  • Patent number: 9479674
    Abstract: A display apparatus includes a display device, obtains first information indicating an error occurring in an electronic apparatus from the electronic apparatus; transmits, to an external information processing apparatus, the obtained first information and second information indicating a display capability of the display device, and obtains third information indicating a manner of dealing with the error occurring in the electronic apparatus. The third information has been transmitted by the external information processing apparatus based on the first information and the second information. The display control part then displays the obtained third information on the display device.
    Type: Grant
    Filed: April 16, 2015
    Date of Patent: October 25, 2016
    Assignee: RICOH COMPANY, LTD.
    Inventor: Ken Norota
  • Patent number: 9454242
    Abstract: The present invention discloses an optical displacement detection apparatus and an optical displacement detection method. The optical displacement detection apparatus includes: a light source for projecting light on a surface; an image capturing unit for generating an image signal according to light reflected from the surface; and a processing unit for generating an auto-exposure (AE) state value and an image quality (IQ) value according to the image signal, and determining an AE range according to an initial AE range, the AE state value and the IQ value.
    Type: Grant
    Filed: March 22, 2013
    Date of Patent: September 27, 2016
    Assignee: PIXART IMAGING INCORPORATION
    Inventors: Yen-Chang Wang, Chun-Wei Chen
  • Patent number: 9213920
    Abstract: Techniques for using infrared imaging to create digital images for use in product customization are described. In an embodiment, an infrared photograph of a product with imprinted markup is received and a visible light photograph of the product with the imprinted markup is received. The imprinted markup is visible in the visible light photograph but is not visible in the infrared photograph. Instructions for rendering a customization image of the product depicting a particular customization are determined based in part on the infrared photograph and visible light photograph, where the particular customization is not in the infrared photograph or the visible light photograph.
    Type: Grant
    Filed: January 8, 2013
    Date of Patent: December 15, 2015
    Assignee: Zazzle.com, Inc.
    Inventors: Young Harvill, Robert I. Beaver, III, Jeffrey J. Beaver
  • Patent number: 9158952
    Abstract: There is set forth herein an indicia reading terminal having a first illumination and exposure control configuration and a second illumination and exposure control configuration, the first illumination and control configuration having a first associated illumination control and a first associated exposure control, the second illumination and exposure control configuration having a second associated illumination control and a second associated exposure control, wherein with the first illumination control active an average energization level of the illumination subsystem during exposure of one or more frames is higher than with the second illumination control active, and wherein with the first exposure control active an average exposure period of the image sensor array is shorter than with the second exposure control active.
    Type: Grant
    Filed: October 7, 2013
    Date of Patent: October 13, 2015
    Assignee: Hand Held Products, Inc
    Inventors: Brian L Jovanovski, Alexey Chernyakov, Daniel Van Volkinburg
  • Patent number: 9159010
    Abstract: A code is applied to a part of the retail item or its packaging/label. The code is applied in a repeat pattern. The code is presented in an optical machine-readable format. Code markers are arranged at pre-defined positions within a matrix. An optical machine-readable orientation device indicates the correct orientation of the matrix, so that the position of the code markers within the correctly orientated matrix corresponds to a pre-defined sequence of code integers. The code corresponds to an existing barcode number for the retail item. The code is presented in a manner discreet enough to be part of the printed design of a label or packaging for the retail item, without changing the overall appearance of the printed design.
    Type: Grant
    Filed: June 10, 2011
    Date of Patent: October 13, 2015
    Assignee: RNIB, Inc.
    Inventor: Duncan Robinson
  • Patent number: 9106783
    Abstract: An image reading apparatus includes a light emitting diode (LED), a carriage, light receiving elements, a clamp circuit, an A/D convertor, and an image correction unit. The image correction unit is configured to: detect a document area where the reflected light is abnormal by comparing first image data with second image data; and replace the first image data corresponding to the abnormal document area with third image data. The first image data is generated by movement of the carriage in a sub-scanning direction of a first direction. The second image data is generated by movement of the carriage in the sub-scanning direction of a second direction at a reduced luminescence level of the capturing light illuminated on the document compared with a luminescence level in the movement of the carriage in the first direction. The third image data is the second image data where at least brightness is adjusted.
    Type: Grant
    Filed: February 28, 2014
    Date of Patent: August 11, 2015
    Assignee: Kyocera Document Solutions Inc.
    Inventor: Haruki Sayama
  • Publication number: 20150093000
    Abstract: Disclosed herein is a medical device including a reader to recognize a command code, and a main body to perform a function matched to the command code recognized by the reader. The medical device may have a small size and be produced at low cost.
    Type: Application
    Filed: October 2, 2014
    Publication date: April 2, 2015
    Inventors: Sang Mok LEE, Dong Gyu HYUN, Jae Moon JO, Seok Won CHOI
  • Patent number: 8995741
    Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.
    Type: Grant
    Filed: August 15, 2014
    Date of Patent: March 31, 2015
    Assignee: Google Inc.
    Inventors: Sanjiv Kumar, Henry Allan Rowley, Xiaohang Wang, Jose Jeronimo Moreira Rodrigues
  • Patent number: 8996351
    Abstract: Techniques are provided for translating a document that was scanned by a multi-function peripheral (MFP). A server within a computing cloud receives an MFP identifier and processed scan data that results from optical character recognition and/or natural language translation having been performed on scan data produced by the MFP. In response to the receipt of the processed scan data at the server, the server selects a set of rules that is mapped to a context to which the MFP identifier is mapped. Corrected processed scan data is generated by applying the set of rules to the processed scan data that was received by the server. Manual corrections made to the corrected processed scan data may be used to update the set of rules so that those corrections are also made to other processed scan data produced by MFPs having identifiers mapped to the same context.
    Type: Grant
    Filed: August 24, 2011
    Date of Patent: March 31, 2015
    Assignee: Ricoh Company, Ltd.
    Inventor: Deeksha Sharma
  • Patent number: 8990112
    Abstract: A system and method for capturing image data is disclosed. A receipt image processing service selects from a repository a template that guides data capture of receipt data from a receipt image and presents the template to a user on an image capture device. A user previews the receipt image and the selected template. If the user decides that the template does not correctly indicate locations of data areas for data items in the receipt image, then the user either updates an existing template or creates a new template that correctly indicates the location of selected data areas in the receipt image. The selected template, the updated template, or the new template is then used to extract receipt data from the receipt image. The receipt data and receipt image data are then provided to the expense report system.
    Type: Grant
    Filed: June 14, 2012
    Date of Patent: March 24, 2015
    Assignee: Ricoh Company, Ltd.
    Inventor: Jayasimha Nuggehalli
  • Patent number: 8976051
    Abstract: Aspects of the present disclosure relate to floating point timers and counters that are used in a variety of contexts. In some implementations, a floating point counter can be used to generate a wave form made up of a series of pulses with different pulse lengths. An array of these floating point counters can be used to implement a pool of delays. In other implementations, an array of floating point counters can be used to analyze waveforms on a number of different communication channels. Analysis of such waveforms may be useful in automotive applications, such as in wheel speed measurement for example, as well as other applications.
    Type: Grant
    Filed: June 5, 2012
    Date of Patent: March 10, 2015
    Assignee: Infineon Technologies AG
    Inventors: Ljudmil Anastasov, Jens Barrenscheen
  • Patent number: 8977072
    Abstract: 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: Grant
    Filed: December 13, 2012
    Date of Patent: March 10, 2015
    Assignee: A9.com, Inc.
    Inventors: Raghavan Manmatha, Mark A. Ruzon
  • Patent number: 8965129
    Abstract: The present invention is related to systems and methods for translating language text on a mobile camera device offline without access to the Internet. More specifically, the present invention relates to systems and methods for displaying text of a first language and a translation of the first language text into a second language text which is displayed in real time in augmented reality on the mobile device. The processing can use a single line or a multiline algorithm designed with a plurality of processing innovations to insure accurate real-time translations without motion jitter. The invention may be used to help travelers in a foreign country with difficulties in reading and understanding text written in the local language of that country. The present invention may be utilized with wearable computers or glasses, producing seamless augmented reality foreign language translations. Some embodiments are particularly useful in translations from Asian languages to English.
    Type: Grant
    Filed: June 14, 2014
    Date of Patent: February 24, 2015
    Assignee: Translate Abroad, Inc.
    Inventors: Ryan Leon Rogowski, Huan-Yu Wu, Kevin Anthony Clark
  • Patent number: 8947745
    Abstract: A imaging scanner identifies first and second locations in a first and second captured image of a document, analyzes each character in the identified locations, and produces a first and second string, each including a character and a confidence value. The device determines that a first measurement of the confidence values in each of the first and second string is beyond a range of a first threshold. The device compares the confidence value for each character in the first string with a corresponding confidence value in the second string, selects a character from one of the first or second string with a higher confidence value; and produces a combined string including the selected characters and the confidence value associated with each selected character.
    Type: Grant
    Filed: July 3, 2013
    Date of Patent: February 3, 2015
    Assignee: Symbol Technologies, Inc.
    Inventor: Ming-Xi Zhao
  • Patent number: 8942481
    Abstract: Disclose embodiments include an image processor for feature detection comprising a single non-planar chip containing a plurality of integrated sensing and processing resources across two or more layers adapted to capture image frames and extract image features. In a particular embodiment, the non-planar chip is a three dimensional CMOS integrated circuit (3D CMOS IC) with vertical distribution of sensing and processing resources across two or more vertical integrated circuit layers. The 3D CMOS IC implements two or more feature detectors in a single chip by reusing a plurality of circuits employed for gradient and keypoint detection. Feature detectors include a scale invariant feature transform detector (SIFT), a Harris-based feature detector, and a Hessian-based feature detector.
    Type: Grant
    Filed: March 11, 2012
    Date of Patent: January 27, 2015
    Assignees: Universidad de Santiago de Compostela, Consejo Superior de Investigaciones Cientificas, Universidad de Sevilla
    Inventors: Manuel Suárez Cambre, Víctor Manuel Brea Sánchez, Fernando Rafael Pardo Seco, Ángel Rodríguez Vázquez, Ricardo Carmona Galán
  • Patent number: 8934676
    Abstract: A method and system for achieving accurate segmentation of characters with respect to a license plate image within a tight bounding box image. A vehicle image can be captured by an image capturing unit and processed utilizing an ALPR unit. A vertical projection histogram can be calculated to produce an initial character boundary (cuts) and local statistical information can be employed to split a large cut and insert a missing character. The cut can be classified as a valid and/or a suspect character and the suspect character can be analyzed. The suspect character can be normalized and passed to an OCR module for decoding and generating a confidence quote with every conclusion. The non-character images can be rejected at the OCR level by enforcing a confidence threshold. An adjoining suspect narrow character can be combined and the OCR confidence of the combined character can be assessed.
    Type: Grant
    Filed: July 2, 2012
    Date of Patent: January 13, 2015
    Assignee: Xerox Corporation
    Inventors: Aaron Michael Burry, Claude Fillion, Vladimir Kozitsky
  • Patent number: 8917936
    Abstract: An image pickup element capture an image of an object, and detailed unique information relating to the captured image is automatically associated with the image through pattern recognition so that the image is easily managed. A pattern detector performs the pattern recognition on an image obtained through a pre-photographing operation, and a result of the recognition is stored in a memory. A code comparator compares stored a preceding recognition result with the latest recognition result obtained through the pattern recognition performed using the pattern detector. In accordance with a result of the comparison, the stored recognition result is updated. When it is determined that a predetermined pattern is not included in the image obtained using the image pickup element, the recognition result stored in the memory is associated with the captured image.
    Type: Grant
    Filed: November 5, 2008
    Date of Patent: December 23, 2014
    Assignee: Canon Kabushiki Kaisha
    Inventor: Futoshi Sasaki
  • Patent number: 8908999
    Abstract: A method, apparatus and program for proofreading a document. The information processor includes a first storage unit for storing output information which includes information text and positional information obtained by performing Optical Character Recognition (OCR) on a source manuscript image. A second storage unit for storing a document file that is proofread by a user, wherein the document file is generated by reading the OCR-processed text according to the order of reading the output information A line movement detection unit for detected movement of a line which includes text in the document file based on the proofreading performed by the user on the document file. A merge unit for reflecting result of the proofreading of the document file in the output information.
    Type: Grant
    Filed: March 5, 2013
    Date of Patent: December 9, 2014
    Assignee: International Business Machines Corporation
    Inventors: Tatsuya Ishihara, Hironobu Takagi
  • Patent number: 8903136
    Abstract: The technology of the present disclosure includes computer-implemented methods, computer program products, and systems to filter images before transmitting to a system for optical character recognition (“OCR”). A user computing device obtains a first image of the card from the digital scan of a physical card and analyzes features of the first image, the analysis being sufficient to determine if the first image is likely to be usable by an OCR algorithm. If the user computing device determines that the first image is likely to be usable, then the first image is transmitted to an OCR system associated with the OCR algorithm. Upon a determination that the first image is unlikely to be usable, a second image of the card from the digital scan of the physical card is analyzed. The optical character recognition system performs an optical character recognition algorithm on the filtered card.
    Type: Grant
    Filed: December 18, 2013
    Date of Patent: December 2, 2014
    Assignee: Google Inc.
    Inventors: Xiaohang Wang, Alessandro Bissacco, Glen Berntson, Marria Nazif, Justin Scheiner, Sam Shih, Mark Leslie Snyder, Daniel Talavera
  • Patent number: 8891822
    Abstract: A system and method for script and orientation detection of images using artificial neural networks (ANNs) are disclosed. In one example, textual content in the image is extracted. Further, a vertical component run (VCR) and horizontal component run (HCR) are obtained by vectorizing each connected component in the extracted textual content. Furthermore, a zonal density run (ZDR) is obtained for each connected component in the extracted textual content. In addition, a concatenated vertical document vector (VDV), horizontal document vector (HDV), and zonal density vector (ZDV) is computed by normalizing the obtained VCR, HCR, and ZDR, respectively, for each connected component. Moreover, the script in the image is determined using a script detection ANN module and the concatenated VDV, HDV, and ZDV of the image. Also, the orientation of the image is determined using an orientation detection ANN module and the concatenated VDV, HDV, and ZDV of the image.
    Type: Grant
    Filed: April 10, 2012
    Date of Patent: November 18, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Chirag Jain, Chanaveeragouda Virupaxgouda Goudar, Kadagattur Gopinatha Srinidhi, Yifeng Wu
  • Patent number: 8891873
    Abstract: A system for document processing including decomposing an image of a document into at least one data entry region sub-image, providing the data entry region sub-image to a data entry clerk available for processing the data entry region sub-image, receiving from the data entry clerk a data entry value associated with the data entry region sub-image, and validating the data entry value.
    Type: Grant
    Filed: July 22, 2013
    Date of Patent: November 18, 2014
    Assignee: Orbograph Ltd
    Inventors: Avikam Baltsan, Ori Sarid, Aryeh Elimelech, Aharon Boker, Zvi Segal, Gideon Miller
  • Patent number: 8891812
    Abstract: A method to secure unique information about a handwritten document and to provide verification of document's authenticity, integrity and non-repudiation. The method includes the following steps: creating a document having an area of interest containing information, segmenting the area of interest on the document into a plurality of elements, obtaining the average gray scale of each element, inserting the average gray scale of each element into an identifier, and attaching the identifier to the document.
    Type: Grant
    Filed: November 9, 2006
    Date of Patent: November 18, 2014
    Assignee: Pitney Bowes Inc.
    Inventors: Andrei Obrea, Christian Crews
  • Patent number: 8891832
    Abstract: In one embodiment, an uploaded multimedia object comprising a photo image or video is subjected to computer vision algorithms to detect and isolate objects within the multimedia object, and the isolated object is searched against a photographic location database containing images of a plurality of locations. Upon detecting a matching object, the location information associated with the photograph in the database containing the matching object may be leveraged to automatically check the user in to the associated location.
    Type: Grant
    Filed: June 3, 2011
    Date of Patent: November 18, 2014
    Assignee: Facebook, Inc.
    Inventor: Erick Tseng
  • Patent number: 8873856
    Abstract: The technology is directed to determining a class associated with an image. In some examples, a method determines the class associated with an image. The method can include determining a segmentation score for an image segment based on a comparison of the image segment and a region of an image. The region of the image can be associated with the image segment. The method further includes determining a confidence score for the image segment based on the segmentation score and a classification score. The classification score can be indicative of a similarity between the image segment and at least one class. The method further includes determining a class associated with the image based on the confidence score. The method further includes outputting the class associated with the image.
    Type: Grant
    Filed: September 9, 2013
    Date of Patent: October 28, 2014
    Assignee: Matrox Electronic Systems, Ltd.
    Inventors: Sylvain Chapleau, Vincent Paquin
  • Patent number: 8873892
    Abstract: A handheld scanner incorporates vision software to allow the handheld scanner to be trained for OCR. The handheld scanner can include a user interface to allow a user to associate an image of a mark with electronic data for the mark. The user interface, along with a range finder, can also be used to influence variables that affect the quality of an image scan, thereby improving the quality of results for the image scan and/or decode process.
    Type: Grant
    Filed: August 21, 2012
    Date of Patent: October 28, 2014
    Assignee: Cognex Corporation
    Inventors: James A. Negro, Carl W. Gerst, III
  • Publication number: 20140314338
    Abstract: A computer-implemented method for providing a text-based representation of a region of interest of an image to first is provided that includes a step of identifying text zones within the image, each text zone including textual content and having a respective rank assigned thereto based on an arrangement of the text zones within the image. The method also includes determining a processing sequence for performing optical character recognition (OCR) on the text zones. The processing sequence is based, firstly, on an arrangement of the text zones with respect to the region of interest and, secondly, on the ranks assigned to the text zones. The method further includes performing an OCR process on the text zones according to the processing sequence to progressively obtain a machine-encoded representation of the region of interest, and concurrently present the machine-encoded representation to the user, via an output device, as the text-based representation.
    Type: Application
    Filed: April 18, 2014
    Publication date: October 23, 2014
    Applicant: TECHNOLOGIES HUMANWARE INC.
    Inventors: Pierre HAMEL, Alain BÉLANGER, Éric BEAUCHAMP
  • Patent number: 8861883
    Abstract: An image processing apparatus includes: a recognition unit that performs character recognition on an image including at least one character and that obtains a score indicating a recognition accuracy of at least one character region extracted through the character recognition; a local blurring-degree computation unit that computes a first degree of blurring of the at least one character region; and a blurring-degree computation unit that computes a second degree of blurring of the image by using the score and the first degree of blurring of the at least one character region.
    Type: Grant
    Filed: June 29, 2012
    Date of Patent: October 14, 2014
    Assignee: Fujitsu Limited
    Inventor: Hiroshi Tanaka
  • Patent number: 8849034
    Abstract: A technique that uses repetitive and reliably recognizable parts of handwriting, during digital handwriting data entry, to trigger recognition of digital ink and to repurpose handwriting task area properties. In one example embodiment, this is achieved by drawing one or more delayed strokes of a desired sub-word unit using a stylus on a touch screen. An associated data of the drawn one or more strokes is inputted via the touch screen into a handwriting recognition engine. A first trigger stroke in the drawn one or more strokes that can be used to trigger the sub-word unit recognition by the handwriting recognition engine is then determined. The sub-word unit recognition is then triggered for the drawn one or more strokes based on the determined first trigger stroke by the handwriting recognition engine.
    Type: Grant
    Filed: December 9, 2004
    Date of Patent: September 30, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventor: Ajay Bhaskarabhatla
  • Publication number: 20140270575
    Abstract: Systems and methods may perform processing associated with receiving, with a capture module in communication with a processor, data. Processing may be performed associated with converting, with an optical character recognition (OCR) module in communication with the capture module and the processor, the data into machine readable data. Processing may be performed associated with extracting, with a processing module in communication with the OCR module and the processor, relevant data from the machine readable data. Processing may be performed associated with populating, with the processing module, a field in a report with the relevant data.
    Type: Application
    Filed: March 14, 2014
    Publication date: September 18, 2014
    Applicant: Concur Technologies, Inc.
    Inventors: Manish RAJKARNIKAR, Sabirhusain Nazirhusain PATEL, Andrew DOTSON, Michael FREDERICKS
  • Patent number: 8836959
    Abstract: A method and apparatus are provided for recognizing characters in a portable terminal with a scan module. Scanned image data is generated by the scan module by scanning a scan target through a scanning-light input/output panel provided on an external surface of the portable terminal as the portable terminal moves across the scan target. Part of the scanned image data is deleted when a current moving speed of the portable terminal is less than a lower limit of an optimal scan speed range, and character recognition is performed on remaining scanned image data. Image data most similar to the scanned image data is detected from a previously stored correction image database when the current moving speed is greater than an upper limit of the optimal scan speed range, and characters corresponding to the detected image data are output as character recognition results.
    Type: Grant
    Filed: February 18, 2010
    Date of Patent: September 16, 2014
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Kyung-Ho Park, Dong-Hyun Lee, Jae-Myung Baek
  • Patent number: 8837818
    Abstract: A feature section including a feature of a candidate region but not including a feature of a related large region is set as for a style type different in feature from the related large region among a plurality of style types, with respect to each index candidate region. At least one or both of the large regions and the candidate regions having the feature included in the set feature section are grouped. An index evaluation degree is calculated, based on the grouped result, with respect to each candidate region. It is determined whether or not a logical element of each candidate region is an index, based on the calculated index evaluation degree.
    Type: Grant
    Filed: March 11, 2010
    Date of Patent: September 16, 2014
    Assignee: Konica Minolta Business Technologies, Inc.
    Inventor: Yoshio Komaki
  • Patent number: 8831329
    Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.
    Type: Grant
    Filed: October 21, 2013
    Date of Patent: September 9, 2014
    Assignee: Google Inc.
    Inventors: Sanjiv Kumar, Henry Allan Rowley, Xiaohang Wang, Jose Jeronimo Moreira Rodrigues
  • Patent number: 8804178
    Abstract: A method for routing a confirmation of receipt of a facsimile or portion thereof according to one embodiment of the present invention includes analyzing text of a facsimile for at least one of a meaning and a context of the text; and routing one or more confirmations to one or more destinations based on the analysis.
    Type: Grant
    Filed: February 25, 2013
    Date of Patent: August 12, 2014
    Assignee: Kofax, Inc.
    Inventors: Roland G. Borrey, Roy Couchman
  • Patent number: 8805125
    Abstract: Comparing extracted card data from a continuous scan comprises receiving, by one or more computing devices, a digital scan of a card; obtaining a plurality of images of the card from the digital scan of the physical card; performing an optical character recognition algorithm on each of the plurality of images; comparing results of the application of the optical character recognition algorithm for each of the plurality of images; determining if a configured threshold of the results for each of the plurality of images match each other; and verifying the results when the results for each of the plurality of images match each other. Threshold confidence level for the extracted card data can be employed to determine the accuracy of the extraction. Data is further extracted from blended images and three-dimensional models of the card. Embossed text and holograms in the images may be used to prevent fraud.
    Type: Grant
    Filed: September 13, 2013
    Date of Patent: August 12, 2014
    Assignee: Google Inc.
    Inventors: Sanjiv Kumar, Henry Allan Rowley, Xiaohang Wang, Yakov Okshtein, Farhan Shamsi, Alessandro Bissacco
  • Patent number: 8798404
    Abstract: A system includes an imaging device and an acquisition layer. The imaging device acquires an image. The acquisition layer is logically located between a source manager and the imaging device, the source manager being called by an application when a user of the system requests to acquire the image. The acquisition layer includes imaging acquisition logic that receives the image from the imaging device and performs optical character recognition (OCR) that extracts machine editable text from the image. The acquisition layer forwards the image to the application and makes the machine editable text available to the user.
    Type: Grant
    Filed: May 26, 2010
    Date of Patent: August 5, 2014
    Inventor: Hin Leong Tan