Document Or Print Quality Inspection (e.g., Newspaper, Photographs, Etc.) Patents (Class 382/112)
  • Patent number: 11108932
    Abstract: An image test apparatus includes an image reader which reads paper on which an image is formed from an image formed surface side to acquire test image data including an entire region of the paper, and a hardware processor which detects a defect in the test image data by comparing the test image data acquired by the image reader with correct image data, the hardware processor detecting a defect in the test image data in a region where the test image data overlaps with the correct image data after aligning positions of the test image data and the correct image data by aligning positions of images to each other.
    Type: Grant
    Filed: June 10, 2019
    Date of Patent: August 31, 2021
    Assignee: KONICA MINOLTA, INC.
    Inventor: Keisuke Morita
  • Patent number: 11104165
    Abstract: Previously, a customer may not have known which information was acquired and may have felt anxiety. In addition, only internal data of the apparatus was previously acquired. However, in order to determine a trouble in the inkjet printer with high precision, visual information such as a state of a printer mechanism or a conveyance line and a print result is also necessary to determine the apparatus state. Therefore, it is necessary to establish a maintenance system capable of acquiring such information.
    Type: Grant
    Filed: March 29, 2016
    Date of Patent: August 31, 2021
    Assignee: Hitachi Industrial Equipment Systems Co., Ltd.
    Inventors: Hiroko Kurihara, Takashi Kawano, Nobuhiro Harada, Kenjiro Fujii, Tomohisa Kohiyama, Makiko Naemura
  • Patent number: 11094048
    Abstract: An image inspection device which enables the user to know the cause of an abnormality in a read image. The image inspection device includes: an image reader outputting a read image generated by reading an image formed on a sheet of paper by an image forming device; an image inspection section inspecting the read image and outputting an inspection result which takes the read image determined not to have an abnormality as a normal image and the read image determined to have the abnormality as an abnormal image; an inspection result report generator generating an inspection result report according to the read image and the inspection result; an inspection result report output section outputting the inspection result report; and a controller performing control to cause the inspection result report output section to output the normal image and the abnormal image in a comparable manner.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: August 17, 2021
    Assignee: Konica Minolta, Inc.
    Inventor: Yasumasa Tsukamoto
  • Patent number: 11080750
    Abstract: A method and associated computer system and computer program product. An image is obtained of a product recommender who is interacting with a product. The product recommender is identified based on the image. Information on the product is provided based on the identified product recommender.
    Type: Grant
    Filed: October 24, 2017
    Date of Patent: August 3, 2021
    Assignee: International Business Machines Corporation
    Inventors: Tina Huang, Sunny Liu, Clement Su, Jason C S Yang
  • Patent number: 11068681
    Abstract: A method for verifying a security document by means of a reading device wherein first transmission and/or reflection properties of a first region of the security document are detected in a first spectral range by the reading device and a first data set specifying these properties is generated therefrom, wherein the first region at least in some regions overlaps an optical security element arranged on the security document or embedded in the security document and wherein second transmission and/or reflection properties of the first region of the security document are detected in a second spectral range by the reading device and a second data set specifying these properties is generated therefrom, wherein the first spectral range differs from the second spectral range, and wherein, the authenticity of the security document and/or of the security element is checked on the basis of at least the first data set and the second data set.
    Type: Grant
    Filed: December 13, 2017
    Date of Patent: July 20, 2021
    Assignees: Kurz Digital Solutions GmbH & Co. KG, OVD Kinegram AG
    Inventors: Uwe Frieser, Michael Grau, René Staub, Michael Hoffmann
  • Patent number: 11032435
    Abstract: A method, computer system, and computer program product for document superposition detection and correction are provided. The embodiment may include receiving a plurality of scanned documents. The embodiment may also include analyzing the plurality of the scanned documents. The embodiment may further include determining if there is a superposition scanning defect within the scanned documents based on the analysis. The embodiment may also include in response to the plurality of the scanned documents containing the superposition scanning defect, identifying a subset of documents within the plurality of scanned documents containing the determined superposition scanning defect. The embodiment may further include transmitting a notification to a user, wherein the notification identifies the subset and that the subset requires a rescan.
    Type: Grant
    Filed: January 16, 2020
    Date of Patent: June 8, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Igor S. Ramos, Andrew J. Lavery, Faheem Altaf, Paul Hake
  • Patent number: 11023708
    Abstract: A computer-implemented method for determining whether images of faces contained in a document correspond to each other. The method comprises acquiring image data pertaining to the document and performing facial detection on the image data to detect one or more facial representations existing within the document. If two or more facial representations are detected, a first facial representation and a second facial representation are selected, and determination of whether the image of a face of the first facial representation corresponds to the image of a face of the second facial representation is performed.
    Type: Grant
    Filed: June 21, 2019
    Date of Patent: June 1, 2021
    Inventors: Christos Sagonas, Joao Silva Gomes, Jacques Cali
  • Patent number: 10953662
    Abstract: The present application discloses an inkjet printing device in which a nozzle that caused a print defect, such as an ejection failure, is reliably identified by a simple process even when an end of a test pattern is not recorded. In a configuration example of the inkjet printing device, a test pattern TPat to be printed for identifying a recording head nozzle that caused a print defect consists of an ejection failure detection pattern DPat and a position detection pattern PPat. The position detection pattern PPat consists of a position mark PM4 and pairs of position marks (PM1 and PM1; PM2 and PM2; and PM3 and PM3) symmetrically arranged with respect to the position mark PM4 in a sheet width direction. Each position mark consists of three linear patterns having the same length and disposed at equal intervals. Moreover, the position detection pattern PPat is configured such that linear pattern length decreases with increasing distance from a center position mark.
    Type: Grant
    Filed: December 9, 2019
    Date of Patent: March 23, 2021
    Assignee: SCREEN HOLDINGS CO., LTD.
    Inventor: Asuka Muramatsu
  • Patent number: 10936866
    Abstract: A method for detecting a document fraud is disclosed. A first image of a first document and a second image of a second document are obtained. A procedure of detection of zones sensitive to document frauds are applied in the regions of the first image and of the second image registered on the first image. Each sensitive zone detected is then divided into a plurality of subparts. A measurement of dissimilarity is calculated between corresponding subparts from the first image and the registered second image. It is then determined whether the first document is identical to the second document from measurements of dissimilarity. If the first document is different from the second document, a level of difference is determined between the first and second documents according to a value representing a proportion of different subparts; and a fraud is detected when the level of difference is below a third predetermined threshold.
    Type: Grant
    Filed: September 27, 2019
    Date of Patent: March 2, 2021
    Assignee: IDEMIA IDENTITY & SECURITY FRANCE
    Inventors: Thibault Berger, Laurent Rostaing, Alain Rouh
  • Patent number: 10922540
    Abstract: Systems and associated methods relate to classification of documents according to their spectral frequency signatures using a deep neural network (DNN) and other forms of spectral analysis. In an illustrative example, a DNN may be trained using a set of predetermined patterns. A trained DNN may, during runtime, receive documents as inputs, where each document has been converted into a spectral format according to a (2D) Fourier transform. Some exemplary methods may extract periodicity/frequency information from the documents based on the spectral signature of each document. A clustering algorithm may be used in clustering/classification of documents, as well as searching for documents similar to a target document(s). A variety of implementations may save significant time to users in organizing, searching, and identifying documents in the areas of mergers and acquisitions, litigation, e-discovery, due diligence, governance, and investigatory activities, for example.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: February 16, 2021
    Inventors: Brent G. Stanley, Joseph Vance Haynes
  • Patent number: 10890870
    Abstract: In one example of the disclosure, a set of scanned images is accessed. The scanned images are scans of distinct printouts of subject images produced utilizing an intermediate transfer member. A set of defect maps is created by comparing the scanned images to reference data for the subject images. The set of defect maps are combined into an integrated defect map. A dent defect on the ITM is identified utilizing the integrated defect map.
    Type: Grant
    Filed: March 30, 2017
    Date of Patent: January 12, 2021
    Assignee: HP INDIGO B.V.
    Inventors: Oded Perry, Oren Haik, Avi Malki
  • Patent number: 10789496
    Abstract: Techniques for assuring the quality of mobile document image captured using a mobile device are provided. These techniques include performing one or more tests to assess the quality of images of documents captured using the mobile device. The tests can be selected based on the type of document that was imaged, the type of mobile application for which the image quality of the mobile image is being assessed, and/or other parameters such as the type of mobile device and/or the characteristics of the camera of the mobile device that was used to capture the image. The image quality assurance techniques can also be implemented on can be implemented on a mobile device and/or on a remote server where the mobile device routes the mobile image to the remote server processing and the test results are be passed from the remote server to the mobile device.
    Type: Grant
    Filed: April 29, 2019
    Date of Patent: September 29, 2020
    Assignee: MITEK SYSTEMS, INC.
    Inventors: Nikolay Kotovich, Grigori Nepomniachtchi, James DeBello
  • Patent number: 10760977
    Abstract: A monitoring system includes an analytical engine system coupled to a plurality of sensors of an engine system. The analytical engine system is configured to determine a model probability distribution based on model data, determine a distance threshold value of the model probability distribution based at least in part on a threshold percentage, determine a window probability distribution based on window data sampled from the engine system, determine a fraction of the window probability distribution that is greater than the distance threshold value, and generate a lubricant alert signal when the fraction is greater than a temperature anomaly threshold. The model data includes model temperature data and model load data. The window data includes window temperature data and window load data that is based at least in part on feedback from the plurality of sensors during operation of the engine system.
    Type: Grant
    Filed: May 17, 2017
    Date of Patent: September 1, 2020
    Assignee: General Electric Company
    Inventors: Subrat Nanda, Douglas David Baptista de Souza, Bruno Paes Leao
  • Patent number: 10735690
    Abstract: A video conferencing may include a virtual whiteboard for displaying annotations and streaming of a physical whiteboard, indexing of physical whiteboard content, and compositing and projection of remote whiteboard content onto a local whiteboard.
    Type: Grant
    Filed: May 6, 2019
    Date of Patent: August 4, 2020
    Assignee: Blue Jeans Network, Inc.
    Inventors: Ashish Nagpal, Alagu Periyannan, Navneet Kumar
  • Patent number: 10726474
    Abstract: Online products and priorities of the online products are obtained, where the online products are waiting to be displayed on a product shelf. The product shelf includes at least two display slots, where each display slot of the at least two display slots displays one online product. An attention ranking of each display slot is determined based on a distance between each display slot and a visual center of the product shelf. An online product is displayed with a higher obtained priority in a particular display slot with a greater determined attention ranking.
    Type: Grant
    Filed: June 22, 2018
    Date of Patent: July 28, 2020
    Assignee: Alibaba Group Holding Limited
    Inventor: Jie Li
  • Patent number: 10719702
    Abstract: Embodiments describing an approach to evaluate text and image consistency. Receiving one or more images. Receiving one or more text documents. Identifying relevant text in the one or more text documents. Determining the consistency between the one or more images and the one or more text documents. Creating one or more image and text consistency scores based on the determined consistency between the one or more images and the one or more text documents, and outputting the one or more image and text consistency scores for evaluating text and image consistency.
    Type: Grant
    Filed: November 8, 2017
    Date of Patent: July 21, 2020
    Assignee: International Business Machines Corporation
    Inventors: Amrita Saha, Srikanth G. Tamilselvam, Pankaj S. Dayama, Priyanka Agrawal
  • Patent number: 10713469
    Abstract: Disclosed in some examples are methods, systems, computing devices, and machine readable mediums that provide for cropping systems that automatically crop digital images using one or more smart cropping techniques. Smart cropping techniques may include: cropping an image based upon emotion detection, cropping based upon facial recognition and matching, and cropping based upon landmark matching. In some examples, a single smart cropping technique may be utilized. In other examples, a combination of the smart cropping techniques may be utilized.
    Type: Grant
    Filed: April 23, 2019
    Date of Patent: July 14, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: David Benjamin Lee, Erez Kikin Gil
  • Patent number: 10708056
    Abstract: An information processing method, a terminal and a computer storage medium are disclosed. Here, the information processing method includes that: information of a first image is pre-acquired, and a first encryption key is generated and stored; information of a second image is acquired; a first image characteristic and second image characteristic of the information of the second image are extracted, wherein the first image characteristic represents background information of the first image, and the second image characteristic represents foreground information of the first image; a third image characteristic is obtained on the basis of the first image characteristic and the second image characteristic, and the third image characteristic is determined as a second encryption key; and similarity matching is performed on the second encryption key and the pre-stored first encryption key to generate a matching result, and a second image is authenticated according to the matching result.
    Type: Grant
    Filed: August 31, 2017
    Date of Patent: July 7, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Zhiguang Qiu, Xin Hou
  • Patent number: 10657635
    Abstract: An inspection apparatus includes circuitry to acquire a reference image used for inspecting a printed matter, acquire a scanned image by scanning the printed matter, generate a difference image indicating a difference between the acquired reference image and the acquired scanned image, extract an edge region from the reference image, detect a proximity region located near the edge region, correct an inspection threshold to be applied to a pixel defining the edge region based on a density difference and a distance between the pixel defining the edge region and an influencing pixel set the proximity region, and an inspection threshold to be applied to a pixel defining the proximity region based on a density difference and a distance between the pixel defining the proximity region and an influencing pixel in the edge region, and inspect the printed matter based on the generated difference image and the corrected inspection threshold.
    Type: Grant
    Filed: March 14, 2018
    Date of Patent: May 19, 2020
    Assignee: Ricoh Company, Ltd.
    Inventor: Hitomi Kaneko
  • Patent number: 10657636
    Abstract: Substrates and technology for detecting printing plate misuse or mismatch. Such misuse or mismatch may result in multiple, different encoded signal being erroneously included in packaging. One claim generally recites a substrate for a package, hang tag or label, the substrate including: barcode including check digit; printed control icon, the printed control icon comprising a design printed with each of four (4) ink separations, the design comprising plurality of design elements, the plurality of design elements comprising a central element, rotation indicator corresponding to the check digit, and a plurality of registration indicators, the four (4) ink separations comprising Cyan (C) color channel, Magenta (M) color channel, Yellow (Y) color channel and Black (K) color channel; in which the printed control icon indicates a printing plate mismatch when it comprises more than one (1) observable rotation indicator. Of course, other features, claims and combinations are described as well.
    Type: Grant
    Filed: October 17, 2017
    Date of Patent: May 19, 2020
    Assignee: Digimarc Corporation
    Inventors: Stephen A. Lauer, Tony F. Rodriguez
  • Patent number: 10650098
    Abstract: Improved techniques for proactive identification of errors are provided. Documents are analyzed, using natural language processing (NLP) models, to identify entities in the documents. The documents are processed with the NLP models to identify relationships among the entities, and each of the entities is stored in a data store, where the data store further includes an indication of the identified relationships among the entities. A draft correspondence is received, and it is determined that the draft correspondence includes a first entity and a second entity, where the first entity and the second entity have a first relationship. Upon determining that the first relationship conflicts with at least one of the relationships stored in the data store, a suggested revision for the draft correspondence is generated.
    Type: Grant
    Filed: June 26, 2018
    Date of Patent: May 12, 2020
    Assignee: International Business Machines Corporation
    Inventors: Kevin M. O'Connell, Brenda Berg, Alex Matos, Janet Cederholm
  • Patent number: 10642553
    Abstract: Provided is an image forming apparatus for allowing easy recognition of an image forming job corresponding to a sheet bundle on a sheet discharge tray. An image region in which an entire configuration of the image forming apparatus and a sheet discharge apparatus is displayed and a list region in which processed image forming jobs are listed are displayed on a monitor screen of the image forming apparatus. In the image region, sheet images corresponding to processed jobs are mapped at corresponding positions of the sheet discharge trays. When a sheet image is designated by a cursor, a processed job corresponding to a cursor position is identified, and a corresponding sheet image is displayed in an emphasized manner with a color different from that for other sheet images.
    Type: Grant
    Filed: January 2, 2019
    Date of Patent: May 5, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Shin Fukuda
  • Patent number: 10621805
    Abstract: A method and system for detecting currency, relates to banknote detectors, to solve the problem of accuracy rate causes the banknote detectors can not be used. The system includes a UV light source, a white light source, an image acquiring device, a controller, and a prompting device. The white light source and the UV light source are faced to each other. A currency detecting channel is formed between the white light source and the UV light source. A micro-switch and a pause switch are located on a controlling loop of the UV light source. A trigger of the micro-switch is located in the currency detecting channel. The pause switch and the micro-switch are in series connection. The image acquiring device and the white light source are located at a same side of the currency detecting channel. The image acquiring device outputs a currency image to a display device.
    Type: Grant
    Filed: October 25, 2018
    Date of Patent: April 14, 2020
    Inventor: Gary Ka Wo Kwok
  • Patent number: 10606824
    Abstract: Approaches provide for updating information associated with points and/or objects of interest, such as businesses and other such entities. For example, an update service can analyze image data to determine visual features of a visual representation of a business. The visual features can be compared to information stored in a database. The information stored in the database can be derived from previously obtained image data that includes visual features corresponding to the business. A change in the visual representation of the business can be determined. The change might be due to, for example, a change in the business operating at that location which can result in a change in the visual appearance of the business; an update to business hours, contact information, or other information. Once the change is determined to at least a threshold amount, an event to update business information (e.g., the name of the business, contact information, images, etc.
    Type: Grant
    Filed: September 9, 2015
    Date of Patent: March 31, 2020
    Assignee: A9.COM, INC.
    Inventors: Kaolin Imago Fire, Mark Jay Nitzberg, Sunil Ramesh
  • Patent number: 10592751
    Abstract: A method of generating a summary of a media file that comprises a plurality of media segments is provided. The method includes calculating, by a neural network, respective importance scores for each of the media segments, based on content features associated with each of the media segments and a targeting approach, selecting a media segment from the media segments, based on the calculated importance scores, generating a caption for the selected media segment based on the content features associated with the selected media segment, and generating a summary of the media file based on the caption.
    Type: Grant
    Filed: February 3, 2017
    Date of Patent: March 17, 2020
    Assignee: FUJI XEROX CO., LTD.
    Inventors: Bor-Chun Chen, Yin-Ying Chen, Francine Chen
  • Patent number: 10565477
    Abstract: Methods and apparatus to automatically generate an image quality metric for an image are provided. An example method includes automatically processing a first medical image using a deployed learning network model to generate an image quality metric for the first medical image, the deployed learning network model generated from a digital learning and improvement factory including a training network, wherein the training network is tuned using a set of labeled reference medical images of a plurality of image types, and wherein a label associated with each of the labeled reference medical images indicates a central tendency metric associated with image quality of the image. The example method includes computing the image quality metric associated with the first medical image using the deployed learning network model by leveraging labels and associated central tendency metrics to determine the associated image quality metric for the first medical image.
    Type: Grant
    Filed: July 15, 2019
    Date of Patent: February 18, 2020
    Assignee: General Electric Company
    Inventors: Jiang Hsieh, Gopal Avinash, Saad Sirohey, Xin Wang, Zhye Yin, Bruno De Man
  • Patent number: 10546171
    Abstract: An anti-counterfeiting method involves carrying out an image processing operation on an image of the printed genuine barcode including superimposing a best-fit grid on the image and extracting edge linearities of a plurality of modules of the image with respect to the best-fit grid; generating a list of the plurality of modules of the image of the printed genuine barcode (sorted based at least in part on the magnitudes of their respective extracted linearities); carrying out the image processing operation on an image of a printed candidate barcode; generating a list for the plurality of modules of the image of the printed candidate barcode (sorted based at least in part on the magnitudes of their respective extracted linearities); in first and second ranges of magnitudes, comparing the sorted list for the image of the printed genuine barcode with the sorted list for the image of the printed candidate barcode.
    Type: Grant
    Filed: August 8, 2019
    Date of Patent: January 28, 2020
    Assignee: SYS-TECH SOLUTIONS, INC.
    Inventor: Michael L. Soborski
  • Patent number: 10509609
    Abstract: An image forming apparatus includes: an image forming part that forms an image on printing paper; an image reader that reads a printed material including the image formed on printing paper by the image forming part; and a hardware processor that determines whether the printed material including the image formed on printing paper by the image forming part is non-defective in accordance with a threshold for determination and read data, the threshold for determination specifying an error margin in a printed state of the printed material including the image formed on printing paper by the image forming part, the read data corresponding to the printed material read by the image reader, wherein the hardware processor performs control to reprint a page on which the printed material including the image formed on printing paper by the image forming part is determined to be defective, and replace the page.
    Type: Grant
    Filed: October 16, 2018
    Date of Patent: December 17, 2019
    Assignee: KONICA MINOLTA, INC.
    Inventor: Shuichi Ito
  • Patent number: 10498811
    Abstract: Methods and apparatuses are described for automatic validation of applications on synchronized mobile devices. A server receives a command associated with a mobile application and a first image file corresponding to a current view of the application from a client computing device. The server transmits the command to a plurality of mobile devices coupled to the server. Each mobile device accesses the application and performs the command against the application. The server receives a second image file from each mobile device that corresponds to a current view of the mobile application on the mobile device. The server extracts a first set of text segments from predefined areas of the first image file and second sets of text segments from predefined areas of each second image file. The server compares the first set and each second set to determine whether a difference exists between the first set and each second set.
    Type: Grant
    Filed: October 14, 2016
    Date of Patent: December 3, 2019
    Assignee: FMR LLC
    Inventors: Numen Hao, Tao Sui, Ji Zhan
  • Patent number: 10486432
    Abstract: An image processing apparatus that generates data for setting different colors for a projected portion and a recessed portion of an unevenness on a surface of a recording medium by recording a colored printing material on at least the projected portion of the unevenness includes a first acquisition unit configured to acquire recording amount data representing a recording amount of the colored printing material, and a halftoning unit configured to perform first halftoning on the recording amount data to arrange a larger number of dots of the colored printing material to be recorded on the projected portion of the unevenness at a center of the projected portion than at edges of the projected portion.
    Type: Grant
    Filed: May 23, 2018
    Date of Patent: November 26, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Toshiyuki Ishii
  • Patent number: 10482173
    Abstract: Example embodiments relate to automated document composition using quality distributions. In example embodiments, each image in a document is processed by determining quality scores that describe image distortion for potential aspect ratios, determining height deviations for the aspect ratios, and generating quality distributions using the height deviations and quality scores. At this stage, a page template is applied to a subset of elements from the document to render a page of the document, and a page score is determined for the page based on, at least, the quality distribution of an image, where the page template is adjusted to include a selected aspect ratio that maximizes the page score of the page.
    Type: Grant
    Filed: June 28, 2013
    Date of Patent: November 19, 2019
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Niranjan Damera Venkata, Ildus Ahmadullin
  • Patent number: 10459931
    Abstract: The disclosure described herein is directed to a computerized system and method of grading and authenticating collectibles utilizing digital imaging devices and processes to provide an objective, standardized, consistent high-resolution grading of collectible objects, such as but not limited to sport and non-sport trading cards. The disclosure eliminates the subjectivity present in the human grading process and overcomes the inherent limitations of the human eye.
    Type: Grant
    Filed: April 27, 2018
    Date of Patent: October 29, 2019
    Assignee: TAG P, LLC.
    Inventors: Stephen Brent Kass, Edward Korbel, Daniel R. Barbakow, Robert Alan Cook, Scot Maxwell, Kate Aplin, Hayden Blauzvern, Megan Shao, Ben Teng, Avi Thaker
  • Patent number: 10460161
    Abstract: Advanced signal processing technology including signal encoding and digital watermarking. Disclosure includes monitoring spectral differences within control strip area to determine signal robustness of encoded signals printed outside of control strip area. Other combinations and technology provided too.
    Type: Grant
    Filed: May 16, 2017
    Date of Patent: October 29, 2019
    Assignee: Digimarc Corporation
    Inventors: Stephen A. Lauer, Jeremy Cattone, Alastair M. Reed, Kristyn R. Falkenstern
  • Patent number: 10445330
    Abstract: The disclosure described herein is directed to a computerized system and method of grading and authenticating collectibles utilizing digital imaging devices and processes to provide an objective, standardized, consistent high-resolution grading of collectible objects, such as but not limited to sport and non-sport trading cards. The disclosure eliminates the subjectivity present in the human grading process and overcomes the inherent limitations of the human eye.
    Type: Grant
    Filed: April 27, 2018
    Date of Patent: October 15, 2019
    Assignee: TAG P, LLC.
    Inventors: Stephen Brent Kass, Edward Korbel, Daniel R. Barbakow, Robert Alan Cook, Scot Maxwell, Kate Aplin, Hayden Blauzvern, Megan Shao, Ben Teng, Avi Thaker
  • Patent number: 10438089
    Abstract: The technology relates to technology for detecting a predetermined image using a template of the predetermined image. The method includes detecting a color, reducing the color to a range of the color, converting to a grayscale plurality of images, extracting at least one edge of the grayscale images, identifying each component in the images, conducting binarization for the each component, obtaining a threshold value, normalizing the template, and matching the template to the predetermined image.
    Type: Grant
    Filed: January 11, 2017
    Date of Patent: October 8, 2019
    Assignee: HENDRICKS CORP. PTE. LTD.
    Inventors: Jason Porter, Michael Michael, Ye Chuanhun, Johannes Sujendro, Foo Yong Yan
  • Patent number: 10410309
    Abstract: The present disclosure describes a method to determine whether a physical identification document is authentic. An authentication manager receives an image of a physical identification document to be authenticated. The authentication manager extracts a set of characteristics of the document from the image. The authentication manager determines a class of the document based on the set of characteristics. The authentication manager applies a convolution kernel, convolving the image with the kernel to generate a feature map. The authentication manager determines a score based on the feature map, where the score identifies the likelihood that the document is valid. The authentication manager then provides an indication that the physical document is authentic based on the score.
    Type: Grant
    Filed: February 26, 2019
    Date of Patent: September 10, 2019
    Assignee: Facebook, Inc.
    Inventors: Raphael A. Rodriguez, Michael Muesch, David Thor, Justin Boyd, Ryan Cahill, Xiaolu Xiong
  • Patent number: 10409530
    Abstract: A printing computing device connects to a multi-function printing (MFP) device to enable additional functionality and capabilities not offered by the MFP device. The printing computing device connects to a network to receive print jobs from external devices within the network. The printing computing device processes the print jobs according to rules such that print jobs are processed accordingly. The printing computing device also includes firmware not available on the MFP device such that print jobs not supported by the MFP device still may be processed. The printing computing device also includes an engine that determines whether an incoming print job is a PDL print job or a command to perform a function not available on the MFP device.
    Type: Grant
    Filed: December 19, 2017
    Date of Patent: September 10, 2019
    Assignee: KYOCERA DOCUMENT SOLUTIONS, INC.
    Inventor: Neil-Paul Bermundo
  • Patent number: 10402654
    Abstract: An image processing method for selecting an image to be output includes evaluating a plurality of first images having a first attribute and a plurality of second images having a second attribute; performing a plurality of selection processes for selecting a plurality of images to be output from among the plurality of first images and the plurality of second images based on evaluation of the plurality of first images and the plurality of second images obtained in the evaluating; and outputting the selected plurality of images. The plurality of selection processes include a selection process for selecting an image to be output from among the plurality of first images by excluding the plurality of second images from selection candidates.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: September 3, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Fumitaka Goto, Hiroyasu Kunieda, Masaaki Obayashi, Maya Kurokawa, Yoshinori Mizoguchi, Masao Kato, Tohru Ikeda
  • Patent number: 10380428
    Abstract: Techniques are described for analyzing a video for memorability, identifying content features of the video that are likely to be memorable, and scoring specific content features within the video for memorability. The techniques can be optionally applied to selected features in the video, thus improving the memorability of the selected features. The features may be organic features of the originally captured video or add-in features provided using an editing tool. The memorability of video features, text features, or both can be improved by analyzing the effects of applying different styles or edits (e.g., sepia tone, image sharpen, image blur, annotation, addition of object) to the content features or to the video in general. Recommendations can then be provided regarding memorability score caused by application of the image styles to the video features.
    Type: Grant
    Filed: September 26, 2017
    Date of Patent: August 13, 2019
    Assignee: Adobe Inc.
    Inventors: Sumit Shekhar, Srinivasa Madhava Phaneendra Angara, Manav Kedia, Dhruv Singal, Akhil Sathyaprakash Shetty
  • Patent number: 10360447
    Abstract: Methods and systems are provided for defining and determining a formal and verifiable mobile document image quality and usability (MDIQU) standard, or Standard for short. The Standard ensures that a mobile image can be used in an appropriate mobile document processing application, for example an application for mobile check deposit. In order to quantify the usability, the Standard establishes 5 quality and usability grades. A mobile image capture device can capture images. A mobile device can receive information associated with one or more image quality assurance (IQA) criteria; evaluating the images to select an image satisfying an image quality criteria based on the received information; and in response to the image satisfying the image quality score, sending the selected image to determine a set of image quality assurance (IQA) scores.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: July 23, 2019
    Assignee: Mitek Systems, Inc.
    Inventors: Grigori Nepomniachtchi, Mike Strange
  • Patent number: 10311322
    Abstract: The present invention relates to a character information recognition method based on image processing. The method comprises: collecting images to obtain a target character image; then sequentially comparing the target character image with character template images in a character template library to find a maximum of a coincidence area of the character in the target character image with the character templates in the character template images; and when the coincidence area meets a preset condition, determining the target character to be recognized as the character in the corresponding character template image. The character templates are designed to include not only a coincidence-permitted region but also a coincidence-restricted region. The coincidence-restricted region is set, so that the direct comparing and matching of the character templates can be more accurately carried out, thereby improving the recognition speed.
    Type: Grant
    Filed: July 14, 2017
    Date of Patent: June 4, 2019
    Assignee: SUNTRONT TECH CO., LTD
    Inventor: Jiheng Fei
  • Patent number: 10289875
    Abstract: Methods and apparatus are disclosed for embedding static information (such as serial numbers, etc.) on objects by modifying their exterior shape slightly, dubbed surface modulation. Data is embedded when the object is created and can then be read using readers with the appropriate resolution. According to one example of the disclosed technology, a method of embedding data expressed as a binary sequence onto an object surface includes establishing a coordinate system over an object surface, computing a transform of the coordinate system to a frequency domain, mapping the binary sequence to an integer value, replacing the highest frequency coefficient of the transform with the integer value, computing an inverse of the transform, producing a vector expressed in the coordinate system, and fabricating at least a portion of the object surface according to the vector.
    Type: Grant
    Filed: July 22, 2016
    Date of Patent: May 14, 2019
    Assignee: Portland State University
    Inventors: Suresh Singh, Farnoosh Moshirfatemi
  • Patent number: 10275673
    Abstract: Techniques for assuring the quality of mobile document image captured using a mobile device are provided. These techniques include performing one or more tests to assess the quality of images of documents captured using the mobile device. The tests can be selected based on the type of document that was imaged, the type of mobile application for which the image quality of the mobile image is being assessed, and/or other parameters such as the type of mobile device and/or the characteristics of the camera of the mobile device that was used to capture the image. The image quality assurance techniques can also be implemented on can be implemented on a mobile device and/or on a remote server where the mobile device routes the mobile image to the remote server processing and the test results are be passed from the remote server to the mobile device.
    Type: Grant
    Filed: June 12, 2017
    Date of Patent: April 30, 2019
    Assignee: Mitek Systems, Inc.
    Inventors: Nikolay Kotovich, Grigori Nepomniachtchi, James DeBello
  • Patent number: 10242921
    Abstract: The method includes classifying sample pattern data into a standard normal group and a standard weak group based on a first criterion. The method further includes extracting a normal group determination function by calculating an image parameter with respect to each piece of sample pattern data included in the standard normal group, and extracting a weak group determination function by calculating the image parameter with respect to each piece of sample pattern data included in the standard weak group. The method also includes classifying the object pattern data into a normal group and a weak group by calculating the image parameter with respect to object pattern data based on a first proximity between the normal group determination function and the object pattern data and a second proximity between the weak group determination function and the object pattern data.
    Type: Grant
    Filed: November 18, 2016
    Date of Patent: March 26, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Sang-Wook Park, Heung-Kook Ko, No-Young Chung
  • Patent number: 10242283
    Abstract: Systems and methods for pre-validating a digital image of an identification (ID) card (e.g., a government-issued passport, driver's license, etc.) are disclosed. A mobile computing device captures image(s) of an ID card. In response, a pre-validation system in communication with the mobile computing device analyzes one or more quality features of the image(s), which includes determining, utilizing a trained neural network (trained using a dataset including images that have been accepted by a post-validation platform and images that have been rejected by the post-validation platform) and based on the one or more quality features, whether at least a first image of the captured image(s) is usable by a remote post-validation process. Responsive to the determining that the at least a first image is usable, the mobile computing device transmits the first image to a remote server for post-validation of the identification card.
    Type: Grant
    Filed: October 3, 2018
    Date of Patent: March 26, 2019
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Chintan Jain, Ryan Fox, Monika Valiramani Boyle
  • Patent number: 10217179
    Abstract: The present disclosure describes systems and methods to classify and authenticate ID documents based on the information contained on the face of the ID document. This present system can automatically classify, authenticate, and extracting data from documents using artificial intelligence (AI) based machine learning for image recognition. In some implementations, the machine learning techniques include a convolutional neural network. The system can also determine the authenticity of other documents, such as currency, stamps, and invoices.
    Type: Grant
    Filed: October 17, 2017
    Date of Patent: February 26, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Raphael A. Rodriguez, Michael Muesch, David Thor, Justin Boyd, Ryan Cahill, Xiaolu Xiong
  • Patent number: 10212299
    Abstract: What is disclosed is a system and method for detecting a folded page in a digital image of a scanned document. In one embodiment, the present method involves receiving a digital image of a document which has been converted to a digitized form using a document scanning device. The digital image is segmented horizontally and vertically to obtain a plurality of image segments. An edge profile is generated for the horizontal and vertical segments. A determination is then made, based on a comparison of the profiles, whether a page fold exists in the digital image. If a page fold is determined to exist in the digital image, the user is notified and the digital image is not sent to a print engine. Otherwise, the digital image is printed.
    Type: Grant
    Filed: February 15, 2017
    Date of Patent: February 19, 2019
    Assignee: Xerox Corporation
    Inventors: Arindam Das, Ravindranath Mannuru
  • Patent number: 10192127
    Abstract: Embodiments of the present invention provide a system for dynamically tuning optical character recognition (OCR) processes. The system receives or captures an image of a resource document and uses a general or default OCR process to identify a source of the document and values of multiple data fields in the image of the document. When the system determines that a data field is missing or cannot be extracted, it causes a computing device to display the image of the resource document and requests user input of a coordinate area of the missing data field from an associated specialist. Once the user input is received, the system applies a data field-specific OCR process on the coordinate area of the missing data field to extract the value of the data field. This value of the missing data field can be transmitted to a processing system for further processing.
    Type: Grant
    Filed: July 24, 2017
    Date of Patent: January 29, 2019
    Assignee: Bank of America Corporation
    Inventors: John B. Hall, Michael J. Pepe, Jr., Murali Santhanam, Kerry Kurt Simpkins
  • Patent number: 10176413
    Abstract: A tamper or copy resistant information bearing device is disclosed. The information bearing device comprises a first data bearing pattern and a second data bearing pattern in overlap. At least a portion of the first data bearing pattern overlaps with at least a portion of the second data bearing pattern to form an overlapping region comprising an overlapped data bearing pattern. At least some information bearing elements of the first type and at least some information bearing elements of the second type in said overlapping data bearing pattern are joined or connected in abutment to form a plurality of overlapped information bearing elements. An overlapped information bearing element comprises a first portion due to said information bearing element of the first type, a second portion due to said information bearing element of the second type, and a third portion due to merging or overlapping of said information bearing element of the first type and said information bearing element of the second type.
    Type: Grant
    Filed: May 22, 2015
    Date of Patent: January 8, 2019
    Assignee: EASY PRINTING NETWORK LIMITED
    Inventors: Tak Wai Lau, Wing Hong Lam
  • Patent number: 10133710
    Abstract: Social networking systems benefit from techniques that improve the ability of users to share online content with other users of a social networking system. In one embodiment, when a user types, pastes, or otherwise inserts a URL, or some other hyperlink, into a message or post to the social networking system, a set of data on the referenced hyperlink target is acquired and stored on a server of the social networking system. The stored data is analyzed, to automatically generate a preview for the hyperlink; and the hyperlink preview is transmitted to the client device for approval. In one embodiment, follow-up actions related to the content are performed when the content is posed, which enables users to perform social graph actions to user nodes and concept nodes related to the message or post. In one embodiment, the shared content is cached on the social networking system.
    Type: Grant
    Filed: February 6, 2014
    Date of Patent: November 20, 2018
    Assignee: FACEBOOK, INC.
    Inventor: Vojin Katic