Unconstrained Handwriting (e.g., Cursive) Patents (Class 382/186)
  • Patent number: 10296788
    Abstract: A minimum edit cost is determined between the candidate string and a model string, where the model string includes at least one blank model character located at a first character position between two consecutive non-blank model characters. The minimum edit cost is representative of a cost of edit operations performed on the candidate string to satisfy characteristics of the model string, and includes: responsive to determining that there is a non-blank candidate character at a second character position of the candidate string and that the second character position is associated with the first character position of the blank model character in the model string, a cost of performing a delete operation of the non-blank candidate character from the candidate string, and a cost of performing an insert operation of a blank character in the candidate string at the second character position are computed, and added to the minimum edit cost.
    Type: Grant
    Filed: December 19, 2016
    Date of Patent: May 21, 2019
    Assignee: MATROX ELECTRONIC SYSTEMS LTD.
    Inventor: Dominique Rivard
  • Patent number: 10289219
    Abstract: Systems and methods of communicating with an unsupported input device to make an application interact with the unsupported input device are described herein. The method comprises obtaining, for the application to be subscribed to the unsupported input device, a mapping of each of a plurality of hotkeys with a corresponding function performed in the application. The method further comprises retrieving a list of universal identifiers, where each of the universal identifiers corresponds to an unsupported input of the unsupported input device. Also, each of the universal identifiers is tagged with a function to be performed in the application in response to the corresponding unsupported input. The method also includes generating a configuration map for the application. The configuration map comprises a mapping of at least one universal identifier, from amongst the list of universal identifiers, with at least one of the plurality of hotkeys.
    Type: Grant
    Filed: October 31, 2013
    Date of Patent: May 14, 2019
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Karthik Jayaraman, Molly Joy
  • Patent number: 10275524
    Abstract: A method for data presentation includes assembling a set of documents in response to a search query by a user having a social network. A respective person is identified with each of a group of documents in the set. For at least one document in the group, a chain of one or more links is found in the social network between the respective person and the user. A search results page is displayed, including an identification of the at least one document together with a sequence of breadcrumbs corresponding to the one or more links in the chain.
    Type: Grant
    Filed: January 23, 2008
    Date of Patent: April 30, 2019
    Assignee: SEARS HOLDINGS MANAGEMENT CORPORATION
    Inventors: Avital Yachin, Sagie Davidovich, Tal Kedar, Yaron Fishman, Liad Agmon
  • Patent number: 10275692
    Abstract: An image recognizing method adopted by a platform is disclosed. The method first receives multiple targets to be recognized at the platform, and inquiries a pre-established semantic tree by reference to the targets for determining if the recognition results of the multiple targets will cause confusion or not. If confusion is not foreseeable, the method obtains respectively a parent-classifier corresponding to each parent-category of each of the targets, and uses the parent-classifiers directly to perform a recognition action to the targets. Otherwise, the method obtains respectively multiple child-classifiers corresponding to multiple subcategories below each of the targets, and uses the multiple child-classifiers to perform such recognition action to the targets.
    Type: Grant
    Filed: February 16, 2017
    Date of Patent: April 30, 2019
    Assignee: VISCOVERY (CAYMAN) HOLDING COMPANY LIMITED
    Inventors: Shao-Hang Hsieh, Yen-Cheng Chen
  • Patent number: 10269120
    Abstract: A character recognition method is provided, including the steps of: recognizing a character string, which includes one or more characters, in a region of interest (ROI) using a first convolutional neural network (CNN) model to generate a recognized character string; and comparing the recognized character string with a plurality of character strings in a character database to find a character string corresponding to the recognized character string, wherein each of the character strings includes one or more characters; wherein if the character string corresponding to the recognized character string is found, the recognized character string is used as a character recognition result, otherwise, using a second CNN model to correct the recognized string and generate a new recognized character string as the character recognition result.
    Type: Grant
    Filed: April 19, 2017
    Date of Patent: April 23, 2019
    Assignee: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
    Inventors: Chih-Chung Kao, Hao-Ping Kang, Jia-Hua Wu
  • Patent number: 10216992
    Abstract: An electronic device is described which has a memory storing an image for display to a user. The device has a shape recognizer which receives drawing input as a result of the user drawing at a location of the displayed image; and a semantic segmentation component which carries out image analysis of the image to compute one or more object classes of objects depicted at the location. The shape recognizer is configured to recognize the drawing input as being in a computed graphical item class of a plurality of pre-specified graphical item classes by analyzing a shape of the drawing input and by using information about the computed object classes of the one or more objects depicted at the drawing input location in the image. The processor is configured to offer at least one graphical item of the computed graphical item class for input to the electronic device.
    Type: Grant
    Filed: November 21, 2016
    Date of Patent: February 26, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: To Tran
  • Patent number: 10192557
    Abstract: A method and an electronic device are provided for voice recognition. A method includes receiving a first voice by one of a first voice recognition device and a second voice recognition device; when the first voice is received by the first voice recognition device and the first voice recognition device recognizes a predetermined command in the first voice, transferring a received second voice to an external electronic device and recognizing the received second voice through the external electronic device; and when the first voice is received by the second voice recognition device and the second voice recognition device recognizes the predetermined command in the first voice, recognizing a second command in the received second voice, and performing an operation based on the recognized second command.
    Type: Grant
    Filed: August 26, 2014
    Date of Patent: January 29, 2019
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Sang-Hoon Lee, Hyuk Kang, Kyung-Tae Kim, Seong-Min Je, Seok-Yeong Jung
  • Patent number: 10133859
    Abstract: Embodiments of the present application relate to a method, apparatus, and system for registering a user identity. The method includes receiving handwriting information associated with handwriting entered by a user, computing a degree of complexity of the first handwriting information, and in the event that the degree of complexity of the first handwriting information satisfies one or more preset conditions, associating the first handwriting information with identity registration information corresponding to the user.
    Type: Grant
    Filed: August 31, 2015
    Date of Patent: November 20, 2018
    Assignee: Alibaba Group Holding Limited
    Inventors: Xuemei Song, Tao Fang
  • Patent number: 10032065
    Abstract: Handwriting verification methods and related computer systems, and handwriting-based user authentication methods and related computer systems are disclosed. A handwriting verification method comprises obtaining a handwriting test sample containing a plurality of available parameters, extracting geometric parameters, deriving geometric features comprising an x-position value and a y-position value for each of a plurality of feature points in the test sample, performing feature matching between geometric features of the test sample and a reference sample, determining a handwriting verification result based at least in part on the feature matching, and outputting the handwriting verification result. Techniques and tools for generating and preserving electronic handwriting data also are disclosed. Raw handwriting data is converted to a streamed format that preserves the original content of the raw handwriting data.
    Type: Grant
    Filed: October 22, 2014
    Date of Patent: July 24, 2018
    Assignee: Wacom Co., Ltd.
    Inventors: Martin Holden, Nicholas Mettyear
  • Patent number: 10032135
    Abstract: Embodiments provide electronic calendar application features and functionality that includes a free form calendar input surface, but the embodiments are not so limited. In an embodiment, a computer-based method can be configured to provide electronic calendar features including a free form calendar surface that enables users to personalize the calendar surface using a variety of input types and methods. Other embodiments are included.
    Type: Grant
    Filed: March 19, 2012
    Date of Patent: July 24, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Chun Hin Nelson Siu, Jonathan Cadiz
  • Patent number: 10007859
    Abstract: A system and method that is able to recognize a user's natural superimposed handwriting without any explicit separation between characters. The system and method is able to process single-stroke and multi-stroke characters. It can also process cursive handwriting. Further, the method and system can determine the boundaries of input words either by the use of a specific user input gesture or by detecting the word boundaries based on language characteristics and properties. The system and method analyzes the handwriting input through the processes of fragmentation, segmentation, character recognition, and language modeling. At least some of these processes occur concurrently through the use of dynamic programming.
    Type: Grant
    Filed: March 28, 2016
    Date of Patent: June 26, 2018
    Assignee: MyScript
    Inventors: Zsolt Wimmer, Freddy Perraud, Pierre-Michel Lallican, Guillermo Aradilla
  • Patent number: 9977976
    Abstract: Disclosed herein is a method that improves the performance of handwriting recognition by calculating path scores so as to identify the path with the highest score as the basis for interpreting handwritten characters. Specifically, the method comprises the following steps: detecting connected regions in an input image comprising handwritten characters; determining a plurality of segmentation positions of the input image; obtaining a plurality of recognition results for each segment of each path in the input image, wherein each recognition result represents a character candidate for the segment and each path comprises one or more segments; obtaining a plurality of scores corresponding to the recognition results; calculating scores for each path in the input image based on segment lengths and the scores corresponding to the recognition results; and using the path with the highest score to interpret the handwritten characters in the input image.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: May 22, 2018
    Assignee: KONICA MINOLTA LABORATORY U.S.A., INC.
    Inventor: Duanduan Yang
  • Patent number: 9965676
    Abstract: A method for identifying reference points in a hand drawing track with a number (n) of dots includes marking a first one of the dots as a reference point; for each of a (kth) one of the dots, determining an included angle; marking the (kth) one of the dots as a reference point when the included angle associated therewith is larger than a predetermined angle; calculating an accumulated distance between the (kth) one of the dots and a last one of the reference point (s) thus marked when the included angle is not larger than the predetermined angle; and marking the (kth) one of the dots as a reference point when it is determined that the accumulated distance thus calculated is larger than the predetermined distance, 2?k?(n?1).
    Type: Grant
    Filed: March 29, 2016
    Date of Patent: May 8, 2018
    Assignee: Zeng Hsing Industrial Co., Ltd.
    Inventors: Zhen-Yu Liu, Jia-Hui You
  • Patent number: 9949107
    Abstract: System and method for detecting an input for an apparatus inside a vehicle, wherein at least one moving user device generates a changing electromagnetic field. A detection unit detects at least one field parameter of the electromagnetic field, wherein the detected field parameter is a function of the geometric arrangement of the user device relative to the detection unit. A radio signature of the user device is determined based on the detected field parameters, and a signature sequence is determined based on a sequence of time-sequentially determined radio signatures of the user device. The determined signature sequence is then assigned to an input gesture, and whereby, based on the input gesture, a signal is generated and output.
    Type: Grant
    Filed: February 8, 2017
    Date of Patent: April 17, 2018
    Assignee: Volkswagen Aktiengesellschaft
    Inventors: Sebastian Gehrling, Klaus Meierling, Gerd Penshorn, Wolfgang Theimer, Jens Kampermann, Matthias Mohaupt, Henning Taschke, Ernst Zielinski
  • Patent number: 9940513
    Abstract: Improved accuracy and user interaction efficiency for selecting a grouping of digital strokes is provided. In response to receiving an indication of a selection input on or in proximity to a digital stroke, a determination is made as to whether the digital stroke is part of an existing group of digital strokes. When the digital stroke is not part of an existing group, an analysis of the digital stroke and other digital strokes within a calculated boundary is performed for determining which strokes should be included in a stroke grouping. A stroke grouping is generated based on the determination. Accordingly, in response to the selection input on or in proximity to the digital stroke, the selection is expanded to the stroke grouping, thus improving the accuracy of the selection gesture and improving computer efficiency.
    Type: Grant
    Filed: July 25, 2016
    Date of Patent: April 10, 2018
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Carine Ramses Iskander, Jie Wu, Ian William Mikutel, Sarah Elizabeth Sykes, David Glen Garber
  • Patent number: 9898186
    Abstract: An apparatus and method for a portable terminal using a touch pen and a handwriting input method using the same are provided. In the apparatus, upon receipt of a handwriting image in an input field provided by an executed application through the touch pen, the received handwriting image is converted to text, the text is inserted in the input field, and the input field with the text is displayed.
    Type: Grant
    Filed: July 12, 2013
    Date of Patent: February 20, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Hwa-Kyung Kim, Joo-Yoon Bae, Ju-Youn Lee, Sung-Soo Kim, Jin-Ha Jun, Sang-Ok Cha
  • Patent number: 9875022
    Abstract: A portable terminal device using a touch pen and a handwriting input method thereof are provided. The handwriting input method of the portable terminal device using a touch pen includes displaying an execution screen of an application on a touch screen in response to the application being executed, overlapping a handwriting input layer, which is configured for a handwriting input, with the execution screen, inputting a handwriting image on an area of the handwriting input layer using the touch pen, determining a data type for recognizing the input handwriting image in consideration of an attribute of the area corresponding to a position in which the handwriting image has been input on the execution screen, and recognizing the input handwriting image as the determined data type, and applying a recognized result of the determined data type to the application.
    Type: Grant
    Filed: October 4, 2016
    Date of Patent: January 23, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jong-woo Jung, In-sik Myung
  • Patent number: 9870197
    Abstract: A buffer receives input from a plurality of objects. A display controller performs control to cause a display unit to display received pieces of input content of the objects in divided frames in time-series order of reception and display received input content additionally in a frame that displays past input content when a specific condition is satisfied.
    Type: Grant
    Filed: October 8, 2015
    Date of Patent: January 16, 2018
    Assignee: FUJITSU LIMITED
    Inventors: Shinichi Ono, Yoshiki Matsuda, Yasuaki Takamoto, Natsue Nakamura
  • Patent number: 9857909
    Abstract: Techniques for determining whether touch-input gestures approximate straight lines and for animating a display with such gestures are described. The techniques determine a linear regression line for pixel locations comprising a gesture, determine distances of the pixel locations from the linear regression line, and render the set of pixel locations to the display based on the distances and a threshold.
    Type: Grant
    Filed: July 31, 2015
    Date of Patent: January 2, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Connor Spencer Blue Worley, Julien George Beguin, Tomer Moscovich
  • Patent number: 9846494
    Abstract: An information processing device, such as a tablet computer or a smartphone, executes diverse processes by an intuitive operation combining a stylus pen and a finger in an input operation of information for performing the startup of an application program, the search for or editing of information, or the like. The information processing device is provided with an information input control program that identifies a first input such as a stylus pen and a second input such as a finger, identifies information input by the first input, recognizes a region designated by the second input, and from the information identified in the recognized region, executes a predetermined process that starts an application program, or searches for or edits information. It is possible to execute diverse processes an intuitive operation using two inputs.
    Type: Grant
    Filed: April 23, 2013
    Date of Patent: December 19, 2017
    Assignee: UEI CORPORATION
    Inventors: Tetsuro Masuda, Makoto Kondo, Hidemi Tsuji, Makoto Hamatsu
  • Patent number: 9807350
    Abstract: Systems and associated methods for capturing media content for a plurality of guests and intelligently parsing the media content to produce a customized/personalized media product for a particular guest or group of guests are described. A system is configured for combining video data and position tracking data to record a group guest experience or show and automatically provide custom media products. Embodiments record a plurality of guests throughout an experience or show, and simultaneously position track each guest individually. Embodiments utilize the tracking data to extract a sub-sampled video of each guest. This sub-sampled video is combined with additional media automatically according to a script. The result is a personalized video take-away for each guest, which can be created entirely without human intervention.
    Type: Grant
    Filed: October 28, 2010
    Date of Patent: October 31, 2017
    Assignee: Disney Enterprises, Inc.
    Inventors: Christopher James Purvis, Joshua B. Gorin, Cliff Wong
  • Patent number: 9754559
    Abstract: An image processing apparatus having a display device displaying a background image and a stroke image superimposed on the background image, the stroke image reproducing a stroke which is drawn by an input operation of a user, includes a recording unit recording image data of the background image and stroke data, which are related to the stroke input by the input operation, into an electronic document; a read unit reading the electronic document; a display unit displaying the background image on the display device by using the image data of the background data, reproducing the stroke image by using the stroke data, and displaying the stroke image superimposed on the background image on the display device; and an edit unit editing the stroke data in accordance with the input operation.
    Type: Grant
    Filed: September 9, 2014
    Date of Patent: September 5, 2017
    Assignee: RICOH COMPANY, LTD.
    Inventors: Mototsugu Emori, Tomoyuki Tsukuda
  • Patent number: 9740928
    Abstract: A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.
    Type: Grant
    Filed: August 31, 2015
    Date of Patent: August 22, 2017
    Assignee: Ancestry.com Operations Inc.
    Inventors: Jack Reese, Michael Murdock, Shawn Reid, Laryn Brown
  • Patent number: 9733764
    Abstract: Aspects include a method, system, and computer program product for determining the position of an object relative to a reflective surface. A method includes acquiring an image of an object and the reflective surface with a camera, the camera positioned adjacent the reflective surface. The object is identified in the image. A reflection of the object on the reflective surface is identified in the image. Three-dimensional coordinates of at least a portion of the object are determined based at least in part on the identifying of the object and the reflection of the object in the image. It is determined when the object is moving relative to the reflective surface. The position of the object is tracked during the movement.
    Type: Grant
    Filed: November 20, 2015
    Date of Patent: August 15, 2017
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Yu Gu, Inseok Hwang, Su Liu, Eric J. Rozner, Yaoguang Wei, Chungkuk Yoo
  • Patent number: 9736291
    Abstract: Systems and methods for pairing electronic devices are provided. In an example embodiment, first motion capture data corresponding to a physical user motion is received from a first device. Second motion capture data corresponding to the physical user motion is received from a second device. Features are extracted from the first motion capture data and the second motion capture data. An association between the first device and the second device is determined based on a comparison of the extracted features. In response to identifying the association between the first and second device, a communicative coupling between the first device and the second device is initiated.
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: August 15, 2017
    Assignee: LinkedIn Corporation
    Inventors: Bowei Gai, Matthew David Shoup, Yevgeniy Brikman
  • Patent number: 9696810
    Abstract: Managing ink content in structured formats on a computing device is provided. Ink content may be received by the computing device. The ink content may then be recognized by the computing device to correspond to a content format associated with one or more applications. The ink content may then be converted by the computing device into a content associated with the one more applications.
    Type: Grant
    Filed: June 11, 2013
    Date of Patent: July 4, 2017
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Nathan J. Fish, Gary L. Caldwell, Oren Trutner, Michael N. Low, Sarah M. Faulkner
  • Patent number: 9692869
    Abstract: Tools (systems, apparatuses, methodologies, computer program products, etc.) for pairing electronic devices including touchscreen-enabled electronic devices, and for facilitating communication between paired electronic devices.
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: June 27, 2017
    Assignee: LinkedIn Corporation
    Inventors: Bowei Gai, Matthew David Shoup
  • Patent number: 9679225
    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: May 26, 2015
    Date of Patent: June 13, 2017
    Assignee: GOOGLE INC.
    Inventors: Sanjiv Kumar, Henry Allan Rowley, Xiaohang Wang, Jose Jeronimo Moreira Rodrigues
  • Patent number: 9672287
    Abstract: A content searching technique that includes sensing at least three types of input gestures from a user, each of the at least three input gestures representative of a respective one of a search term, a class of assets to be searched and a location to be searched. The sensed at least three types of input gestures are translated into the search term, the class of assets to be searched and the location to be searched. The specified location is searched for the class of assets corresponding to the search term. A list of assets residing or available from at the searched location corresponding to the search term are presented in a user interface display.
    Type: Grant
    Filed: December 26, 2013
    Date of Patent: June 6, 2017
    Assignee: THOMSON LICENSING
    Inventor: Juan M. Noguerol
  • Patent number: 9648059
    Abstract: A multi-user CAx editing system may comprise a plurality of editing clients and a collaborative editing server. The server and editing clients may be collectively configured to: a) assign a feature to a first user, detect an attempt to edit the feature by a second user, and reassign the feature to the second user if the first user indicates that the feature may be reassigned, and/or b) detect an editing conflict between a first and second user for a feature and send a reversion request for the feature to one or more clients and/or c) initiate changes for a feature within a remote instance of the electronic model edited by another user and initiate reversion of the changes for the feature within a local instance of the electronic model in response to determining that the changes to the feature within the remote instance of the electronic model generated an error.
    Type: Grant
    Filed: February 5, 2014
    Date of Patent: May 9, 2017
    Assignee: BRIGHAM YOUNG UNIVERSITY
    Inventors: Thomas Trevor Nysetvold, Ammon Hepworth, Charles Gregory Jensen
  • Patent number: 9632691
    Abstract: A non-transitory computer-readable medium storing a selected character specification program that causes a computer to execute a process including detecting a character region indicating a region, in which each character of the displayed character string is displayed on a screen, based on character string display information, specifying a stroke of a closed curved line designated on the screen based on input operation information, and specifying one or a plurality of successive characters, in which a ratio of an area of a selected region based on uppermost, lowermost, leftmost, and rightmost points of the stroke of the closed curved line in the character region to an area of the character region exceeds a threshold, as selected character among a respective character of the displayed character string overlapped with the stroke of the closed curved line.
    Type: Grant
    Filed: July 16, 2014
    Date of Patent: April 25, 2017
    Assignee: FUJITSU LIMITED
    Inventors: Hiroshi Masago, Hideto Higashi, Masahiro Kataoka
  • Patent number: 9633191
    Abstract: While an electronic device with a display and a touch-sensitive surface is in a screen reader accessibility mode, the device displays an application launcher screen including a plurality of application icons. A respective application icon corresponds to a respective application stored in the device. The device detects a sequence of one or more gestures on the touch-sensitive surface that correspond to one or more characters. A respective gesture that corresponds to a respective character is a single finger gesture that moves across the touch-sensitive surface along a respective path that corresponds to the respective character. The device determines whether the detected sequence of one or more gestures corresponds to a respective application icon of the plurality of application icons, and, in response to determining that the detected sequence of one or more gestures corresponds to the respective application icon, performs a predefined operation associated with the respective application icon.
    Type: Grant
    Filed: October 17, 2014
    Date of Patent: April 25, 2017
    Assignee: APPLE INC.
    Inventors: Christopher B. Fleizach, Darren C. Minifie, Gregory F. Hughes, Ryan N. Dour, Ian M. Fisch, Joel M. Lopes Da Silva, Michael M. Pedersen, II, Eric T. Seymour, Devang K. Naik, Ryan S. Dixon
  • Patent number: 9589074
    Abstract: A method of identifying duplicate crash dumps in a computer system may include receiving a first crash dump caused by an application crash, extracting a first function signature of a function that caused the first crash dump, and searching a datastore of crash dumps for function signatures that substantially match the first function signature. The searching may include performing an approximate string-match between each of the function signatures the first function signature and performing an exact string match between each of the function signatures and the first function signature. The searching may also include combining weighted results of the approximate string-match with weighted results of the exact string match to generate match scores for each of the function signatures, and identifying the function signatures that substantially match the first function signature based on the match scores.
    Type: Grant
    Filed: August 20, 2014
    Date of Patent: March 7, 2017
    Assignee: ORACLE INTERNATIONAL CORPORATION
    Inventors: Abhijit Bhattacharjee, Pradeep Kumar
  • Patent number: 9572028
    Abstract: A method, and a mobile device adapted thereto, verifies a user and executes applications via handwriting recognition. The method of controlling a mobile device includes entering a lock state, detecting a user's input, verifying a user based on the input and searching for an instruction corresponding to the input, and performing at least one of maintaining or releasing the lock state and which performs an operation corresponding to the instruction, based on user verification result and the instruction search result.
    Type: Grant
    Filed: March 6, 2013
    Date of Patent: February 14, 2017
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Sangho Kim, Musik Kwon, Moorim Kim, Seongtaek Hwang
  • Patent number: 9569101
    Abstract: A handwriting-based User Interface (UI) apparatus and a method for executing an intended function menu using notes stored in a user terminal supporting a handwriting-based memo function are provided, in which upon user request, a note that has been written by the memo function and stored is retrieved and displayed on a screen. A whole or part of the contents of the displayed note are selected by a first input form. The contents of a note written on the screen by the memo function is designated as a command to execute for the selected whole or part of the contents by a second input form different from the first input form. The selected whole or part of the contents are processed according to the command.
    Type: Grant
    Filed: August 30, 2013
    Date of Patent: February 14, 2017
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Hwa-Kyung Kim, Sung-Soo Kim, Joo-Yoon Bae
  • Patent number: 9536180
    Abstract: Methods and systems for grapheme splitting of text input for recognition are provided. A method may include receiving a text input in a script and segmenting the text input into one or more graphemes. Each of the one or more graphemes may be split into one or more recognition units based on one or more recognition unit identification criteria associated with the script. Next, a text recognition system may be trained using the recognition units. Text input may be handwritten text input received from a user or a scanned image of text.
    Type: Grant
    Filed: December 30, 2013
    Date of Patent: January 3, 2017
    Assignee: Google Inc.
    Inventors: Thomas Deselaers, Daniel Martin Keysers, Dmitriy Genzel, Ashok Chhabedia Popat
  • Patent number: 9501708
    Abstract: A text-recognition system and method include a trained classifier configured to identify a font of a frame of text line image. The system also includes an adaptive sliding window configured to divide the frame into a plurality of cells. A first cell is located around a prominent writing line of the text line image. Additional cells are located above the prominent writing line and below the prominent writing line, such that each of the additional cells above the prominent writing line has a same percentage of ink-pixels and each of the additional cells below the prominent writing line has a same percentage of ink-pixels. The system also includes a font-specific feature parameters database configured for extraction of text features from each of the cells. The system also includes one or more trained font-specific recognizers configured to recognize the extracted text features using an associated font-specific recognizer for the identified font.
    Type: Grant
    Filed: September 10, 2015
    Date of Patent: November 22, 2016
    Assignee: King Fahd University of Petroleum and Minerals
    Inventors: Irfan Ahmad, Sabri A. Mahmoud
  • Patent number: 9503612
    Abstract: Mitigating glare in connection with photographing a document using a camera includes assessing a first amount of glare that would result if a user were to take a snapshot at a first camera position and lighting conditions, if the first amount of glare is below a predetermined threshold, taking a snapshot with the camera, and, if the first amount of glare is above the predetermined threshold, continuously prompting the user to adjust a position of the camera and taking the snapshot when the camera is in a second position and a second amount of glare, different from the first amount of glare, is below the predetermined threshold. The lighting conditions may include effects of external lighting sources. The user may adjust the external lighting sources before taking the snapshot. The lighting conditions may include effects of an internal light source of the camera.
    Type: Grant
    Filed: October 13, 2015
    Date of Patent: November 22, 2016
    Assignee: Evernote Corporation
    Inventors: Alexander Pashintsev, Boris Gorbatov
  • Patent number: 9495096
    Abstract: A mobile terminal and controlling method thereof are disclosed, by which a handwriting input is enabled and by which a handwritten character saved as an image can be further utilized. According to the present invention, when a user directly inputs a character by handwriting, a text corresponding to each handwritten character is saved by being linked to the handwritten character. The user is facilitated to correctly search handwritten characters saved as image for a specific word or the like using the saved confirmed text. By mapping the handwritten character saved as the image correctly using the saved confirmed text, the handwritten character is modifiable or utilizable in various ways. Therefore, a handwritten character saved as an image in a mobile terminal can be further utilized.
    Type: Grant
    Filed: February 26, 2013
    Date of Patent: November 15, 2016
    Assignee: LG ELECTRONICS INC.
    Inventor: Taeyong Kim
  • Patent number: 9489126
    Abstract: A portable terminal device using a touch pen and a handwriting input method thereof are provided. The handwriting input method of the portable terminal device using a touch pen includes displaying an execution screen of an application on a touch screen in response to the application being executed, overlapping a handwriting input layer, which is configured for a handwriting input, with the execution screen, inputting a handwriting image on an area of the handwriting input layer using the touch pen, determining a data type for recognizing the input handwriting image in consideration of an attribute of the area corresponding to a position in which the handwriting image has been input on the execution screen, and recognizing the input handwriting image as the determined data type, and applying a recognized result of the determined data type to the application.
    Type: Grant
    Filed: April 17, 2014
    Date of Patent: November 8, 2016
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jong-woo Jung, In-sik Myung
  • Patent number: 9466295
    Abstract: A natural language dialog system and a method capable of correcting a speech response are provided. The method includes following steps. A first speech input is received. At least one keyword included in the first speech input is parsed to obtain a candidate list having at least one report answers. One of the report answers is selected from the candidate list as a first report answer, and a first speech response is output according to the first report answer. A second speech input is received and parsed to determine whether the first report answer is correct. If the first report answer is incorrect, another report answer other than the first report answer is selected from the candidate list as a second report answer. According to the second report answer, a second speech response is output.
    Type: Grant
    Filed: December 30, 2013
    Date of Patent: October 11, 2016
    Assignee: VIA Technologies, Inc.
    Inventor: Guo-Feng Zhang
  • Patent number: 9424477
    Abstract: According to one embodiment, a handwritten character retrieval apparatus is provided with an acquisition unit, a feature extraction unit, an segmentation unit, a attribute append unit and a retrieval unit. The acquisition unit acquires a handwritten character string in units of a stroke. The feature extraction unit extracts a first feature value unique to each of the strokes from the handwritten character string. The segmentation unit segments the strokes into a plurality of sets. The attribute append unit appends a second feature value based on the sets to each of the strokes. The retrieval unit executes retrieval based on the first feature value and the second feature value.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: August 23, 2016
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Tomoyuki Shibata, Yojiro Tonouchi, Kazunori Imoto, Yasunobu Yamauchi
  • Patent number: 9405997
    Abstract: Systems and methods for analyzing letters in an image of text are described. For each letter, a number of properties are determined and the letters are classified into letterform classes. The properties may include independent letter properties based on only the letter itself, such as a slanted bounding box encompassing the letter. The properties may also include dependent letter properties that are based, in part, on other letters, such as adjacent letters or letters in the same word or line.
    Type: Grant
    Filed: June 17, 2014
    Date of Patent: August 2, 2016
    Assignee: Amazon Technologies, Inc.
    Inventor: Vasanth Elancheralathan
  • Patent number: 9396405
    Abstract: There are provided an operation unit configured to detect a designation area designated on a display screen of a display unit, a specifying unit configured to acquire designation area image position information representing a position corresponding to the designation area in a camera image for each detected designation area, an image segmentation processing unit configured to segment an image corresponding to the designation area from the camera image based on the designation area image position information, a memory unit configured to save image data of the image corresponding to the designation area segmented from the camera image, and a processing control unit configured to activate each of the specifying unit configured to acquire the designation area image position information of the designation area and the processing unit configured to segment the image corresponding to the designation area to be executed for each designation area when the designation area has been designated.
    Type: Grant
    Filed: August 20, 2012
    Date of Patent: July 19, 2016
    Assignee: NEC Corporation
    Inventor: Aki Tanaka
  • Patent number: 9395204
    Abstract: A sketch that includes a graphical chart representation can be received. A dataset can be automatically generated from the sketch can be received. Additionally, a graphical chart can be automatically generated from the sketch. The graphical chart can represent the sketch, and the dataset can include data represented in the graphical chart.
    Type: Grant
    Filed: October 16, 2012
    Date of Patent: July 19, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: Brian Albrecht
  • Patent number: 9390715
    Abstract: A mobile terminal including a wireless communication unit configured to perform wireless communication; a microphone configured to receive an input voice; a touch screen; and a controller configured to receive a written touch input on the touch screen corresponding to the input voice, recognize the input voice while a voice recognition mode is activated, and display extracted information extracted from the recognized input voice on the touch screen based on a comparison of the recognized input voice and the written input.
    Type: Grant
    Filed: May 7, 2014
    Date of Patent: July 12, 2016
    Assignee: LG ELECTRONICS INC.
    Inventor: Hyunjoo Jeon
  • Patent number: 9330086
    Abstract: A method and apparatus for identifying a language used in a document based on a number of strokes per character is provided herein. Once identified, character recognition may take place based on the language identified. In one embodiment, a character recognition engine is utilized for character recognition, wherein the character recognition engine is specifically tailored to the identified language.
    Type: Grant
    Filed: October 10, 2012
    Date of Patent: May 3, 2016
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Ming-Xi Zhao, Shi-Jie Chen, Qi-Zhen He, Wei Lin
  • Patent number: 9329698
    Abstract: A key input control apparatus includes a gesture recognizing unit which detects whether or not an input of a touch event generated on a screen corresponds to a predetermined gesture. A gesture area identifying unit which identifies a predetermined area where the input of the touch event corresponding to the predetermined gesture is generated. A key input recognizing unit which recognizes a hardware key allotted to the predetermined area and performs an operation corresponding to an input of the recognized hardware key.
    Type: Grant
    Filed: August 29, 2013
    Date of Patent: May 3, 2016
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Dong-Jun Lee, Chul-Hui Park, In-Ho Lee, Hye-Soon Jeong, Sun-Yeal Hong
  • Patent number: 9304682
    Abstract: A canvas in an inking application is created and manipulated based on ink strokes. An ink stroke outside a presented canvas, even outside a user interface of the inking application, is recorded and the presented canvas enlarged to cover the recorded ink stroke. If the ink stroke begins on a command area such as a canvas size control icon, the command associated with the area is executed. If the ink stroke begins in a typed text area, lines are frozen and separated responsive to the first stroke. A new canvas is presented between the separated lines. A size of the new canvas is adjusted based on ink entry or a size of the first ink stroke.
    Type: Grant
    Filed: July 26, 2010
    Date of Patent: April 5, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Crystal L. Hoyer, Clifton W. Owen, Howard L. Cooperstein, Steven A. Breinberg, Guem R. Kim
  • Patent number: 9274624
    Abstract: A computer-implemented method comprising receiving, at a tablet display unit of a first tablet that is coupled to a host computer, image data representing a selected portion of a common display file that is stored on an administrator computer; displaying the image data on a stroke-sensitive display of the tablet display unit; receiving user input from the stroke-sensitive display of the tablet display unit and representing handwritten strokes; transmitting the user input to the administrator computer; receiving, from the administrator computer, second image data representing strokes that other users have applied to the same image data using other tablets that are coupled to the administrator computer over a network; displaying, on the stroke-sensitive display, the second image data; storing, in a memory of the tablet display unit, a data file based at least upon the user input and the image data.
    Type: Grant
    Filed: March 31, 2009
    Date of Patent: March 1, 2016
    Assignee: Ricoh Company, Ltd.
    Inventors: Kurt W. Piersol, John W. Barrus, Ken F. Gudan