Patents by Inventor Matthew R. Casey
Matthew R. Casey has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 9053350Abstract: OCR errors are identified and corrected through learning. An error probability estimator is trained using ground truths to learn error probability estimation. Multiple OCR engines process a text image, and convert it into texts. The error probability estimator compares the outcomes of the multiple OCR engines for mismatches, and determines an error probability for each of the mismatches. If the error probability of a mismatch exceeds an error probability threshold, a suspect is generated and grouped together with similar suspects in a cluster. A question for the cluster is generated and rendered to a human operator for answering. The answer from the human operator is then applied to all suspects in the cluster to correct OCR errors in the resulting text. The answer is also used to further train the error probability estimator.Type: GrantFiled: September 14, 2012Date of Patent: June 9, 2015Assignee: Google Inc.Inventors: Ahmad E. Abdulkader, Matthew R. Casey
-
Publication number: 20150112972Abstract: A system and method of identifying objects is provided. In one aspect, the system and method includes a hand-held device with a display, camera and processor. As the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. The processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. The display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.Type: ApplicationFiled: November 14, 2014Publication date: April 23, 2015Inventors: David Petrou, Matthew J. Bridges, Shailesh Nalawadi, Hartwig Adam, Matthew R. Casey, Hartmut Neven, Andrew Harp
-
Patent number: 8977639Abstract: A server system receives a visual query and identifies an entity in the visual query. The server system further identifies a client-side action corresponding to the identified entity and creates an actionable search result element configured to launch the client-side action. Examples of actionable search result elements are buttons to initiate a telephone call, to initiate email message, to map an address, to make a restaurant reservation, and to provide an option to purchase a product. The entity identified in the visual query may be indirectly associated with a client-side action whose contact address or appropriate link is found in a search result associated with the identified entity. The client system receives and displays the actionable search result element, and upon a user selection of the actionable search result element, launches the client-side action in an application distinct from the visual query client application.Type: GrantFiled: August 11, 2010Date of Patent: March 10, 2015Assignee: Google Inc.Inventors: David Petrou, Avi Flamholz, Matthew R. Casey, Theodore Power
-
Patent number: 8891907Abstract: A system and method of identifying objects is provided. In one aspect, the system and method includes a hand-held device with a display, camera and processor. As the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. The processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. The display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.Type: GrantFiled: December 4, 2012Date of Patent: November 18, 2014Assignee: Google Inc.Inventors: David Petrou, Matthew Bridges, Shailesh Nalawadi, Hartwig Adam, Matthew R. Casey, Hartmut Neven, Andrew Harp
-
Publication number: 20140334746Abstract: A server system receives a visual query from a client system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query. The server system also produces structural information associated with the textual characters in the visual query. Textual characters in the plurality of textual characters are scored. The method further includes identifying, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query. A canonical document that includes the one or more high quality textual strings and that is consistent with the structural information is retrieved. At least a portion of the canonical document is sent to the client system.Type: ApplicationFiled: July 29, 2014Publication date: November 13, 2014Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Patent number: 8832804Abstract: A computer implemented system and method are provided for password pre-verification on the client side in client-server applications. An example system comprises a translation module configured to translate user input, in the form of a character string that can represent a password, to obtain a symbolic representation of the user input. The example system also comprises an output module configured to receive the symbolic representation from the translation module and, based on the user input, provide output to the user in the form of visual, audio or haptic cues. Such cues can alert a user as to whether or not the input character string is correctly entered. In a further example embodiment, a system can further comprise a comparison module configured to compare an existing symbolic representation with the symbolic representation generated from the user input by the translation module.Type: GrantFiled: August 5, 2011Date of Patent: September 9, 2014Assignee: Google Inc.Inventors: Matthew R. Casey, Girts Folkmanis, John Mishanski
-
Patent number: 8811742Abstract: A server system receives a visual query from a client system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query. The server system also produces structural information associated with the textual characters in the visual query. Textual characters in the plurality of textual characters are scored. The method further includes identifying, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query. A canonical document that includes the one or more high quality textual strings and that is consistent with the structural information is retrieved. At least a portion of the canonical document is sent to the client system.Type: GrantFiled: December 1, 2011Date of Patent: August 19, 2014Assignee: Google Inc.Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Patent number: 8805079Abstract: A server system receives a visual query from a client system distinct from the server system. The server system performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query. The server system scores each textual character in the plurality of textual characters in accordance with the geographic location of the client system. The server system identifies, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query. Then the server system retrieves a canonical document having the one or more high quality textual strings and sends at least a portion of the canonical document to the client system.Type: GrantFiled: December 1, 2011Date of Patent: August 12, 2014Assignee: Google Inc.Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Publication number: 20130212454Abstract: An e-book system receives and stores different versions of an e-book supporting different consumption modes. Additionally, the e-book system stores signposts for the e-book. The signposts include corresponding locations in different versions of the e-book. When a user switches from a first version to a second version, the e-book system determines based on the signposts a location in the second version of the e-book that corresponds to the current location in the first version. The e-book system then presents the content in the second version from the determined location.Type: ApplicationFiled: February 13, 2012Publication date: August 15, 2013Applicant: GOOGLE INC.Inventor: Matthew R. Casey
-
Publication number: 20130188886Abstract: A system and method of identifying objects is provided. In one aspect, the system and method includes a hand-held device with a display, camera and processor. As the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. The processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. The display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.Type: ApplicationFiled: December 4, 2012Publication date: July 25, 2013Inventors: David Petrou, Matthew Bridges, Shailesh Nalawadi, Hartwig Adam, Matthew R. Casey, Hartmut Neven, Andrew Harp
-
Patent number: 8331739Abstract: OCR errors are identified and corrected through learning. An error probability estimator is trained using ground truths to learn error probability estimation. Multiple OCR engines process a text image, and convert it into texts. The error probability estimator compares the outcomes of the multiple OCR engines for mismatches, and determines an error probability for each of the mismatches. If the error probability of a mismatch exceeds an error probability threshold, a suspect is generated and grouped together with similar suspects in a cluster. A question for the cluster is generated and rendered to a human operator for answering. The answer from the human operator is then applied to all suspects in the cluster to correct OCR errors in the resulting text. The answer is also used to further train the error probability estimator.Type: GrantFiled: January 21, 2009Date of Patent: December 11, 2012Assignee: Google Inc.Inventors: Ahmad Abdulkader, Matthew R. Casey
-
Publication number: 20120134590Abstract: A server system receives a visual query from a client system distinct from the server system. The server system performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query. The server system scores each textual character in the plurality of textual characters in accordance with the geographic location of the client system. The server system identifies, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query. Then the server system retrieves a canonical document having the one or more high quality textual strings and sends at least a portion of the canonical document to the client system.Type: ApplicationFiled: December 1, 2011Publication date: May 31, 2012Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Publication number: 20120128250Abstract: A server system receives a visual query from a client system distinct from the server system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query, and scores each textual character in the plurality of textual characters. The server system identifies, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query; retrieves a canonical document having the one or more high quality textual strings; generates a combination of the visual query and at least a portion of the canonical document; and sends the combination to the client system.Type: ApplicationFiled: December 1, 2011Publication date: May 24, 2012Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Publication number: 20120128251Abstract: A server system receives a visual query from a client system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query. The server system also produces structural information associated with the textual characters in the visual query. Textual characters in the plurality of textual characters are scored. The method further includes identifying, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query. A canonical document that includes the one or more high quality textual strings and that is consistent with the structural information is retrieved. At least a portion of the canonical document is sent to the client system.Type: ApplicationFiled: December 1, 2011Publication date: May 24, 2012Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Publication number: 20110129153Abstract: A server system receives a visual query from a client system. The visual query is an image containing text such as a picture of a document. At the receiving server or another server, optical character recognition (OCR) is performed on the visual query to produce text recognition data representing textual characters. Each character in a contiguous region of the visual query is individually scored according to its quality. The quality score of a respective character is influenced by the quality scores of neighboring or nearby characters. Using the scores, one or more high quality strings of characters are identified. Each high quality string has a plurality of high quality characters. A canonical document containing the one or more high quality textual strings is retrieved. At least a portion of the canonical document is sent to the client system.Type: ApplicationFiled: August 6, 2010Publication date: June 2, 2011Inventors: David Petrou, Ashok C. Popat, Matthew R. Casey
-
Publication number: 20110131241Abstract: A server system receives a visual query and identifies an entity in the visual query. The server system further identifies a client-side action corresponding to the identified entity and creates an actionable search result element configured to launch the client-side action. Examples of actionable search result elements are buttons to initiate a telephone call, to initiate email message, to map an address, to make a restaurant reservation, and to provide an option to purchase a product. The entity identified in the visual query may be indirectly associated with a client-side action whose contact address or appropriate link is found in a search result associated with the identified entity. The client system receives and displays the actionable search result element, and upon a user selection of the actionable search result element, launches the client-side action in an application distinct from the visual query client application.Type: ApplicationFiled: August 11, 2010Publication date: June 2, 2011Inventors: David Petrou, Avi Flamholz, Matthew R. Casey, Theodore Power