Patents by Inventor Raymond W. Smith
Raymond W. Smith 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: 9436886Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: GrantFiled: March 17, 2015Date of Patent: September 6, 2016Assignee: Google Inc.Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong Man Cheung, Andrea Frome, Shlomo Urbach
-
Publication number: 20160188991Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: ApplicationFiled: March 17, 2015Publication date: June 30, 2016Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong Man Cheung, Andrea Frome, Shlomo Urbach
-
Patent number: 9020265Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: GrantFiled: June 5, 2014Date of Patent: April 28, 2015Assignee: Google Inc.Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong Man Cheung, Andrea Frome, Shlomo Urbach
-
Publication number: 20140286573Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: ApplicationFiled: June 5, 2014Publication date: September 25, 2014Applicant: GOOGLE INC.Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong Man Cheung, Andrea Frome, Shlomo Urbach
-
Patent number: 8787673Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: GrantFiled: July 12, 2011Date of Patent: July 22, 2014Assignee: Google Inc.Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong man Cheung, Andrea Frome, Shlomo Urbach
-
Patent number: 8744171Abstract: A page layout module receives a page image displaying text in an unknown script and unknown orientation, determines a text section in the received image and transmits the text section to an orientation and script module. The orientation and script module comprises a training module, a classifier and a recognition module. The training module trains the classifier to identify connected components that include a connected portion of one or more characters of text. The recognition module uses the trained classifier to identify in the received text section a set of connected components. The recognition determines the likely orientation and script for the connected components and then uses the determined information to determine the orientation and script for the text section. The determined orientation and script for the text section is transmitted to the OCR module. The OCR module uses the determined orientation and script to recognize text in the text section.Type: GrantFiled: March 24, 2010Date of Patent: June 3, 2014Assignee: Google Inc.Inventors: Raymond W. Smith, Ranjith Unnikrishnan
-
Patent number: 8666174Abstract: Systems, methods and computer program products on storage devices for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.Type: GrantFiled: January 17, 2012Date of Patent: March 4, 2014Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Publication number: 20120114243Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.Type: ApplicationFiled: January 17, 2012Publication date: May 10, 2012Applicant: GOOGLE INC.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 8175394Abstract: Systems, methods and computer program products on storage devices for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.Type: GrantFiled: September 8, 2006Date of Patent: May 8, 2012Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 8170351Abstract: Systems, methods, and computer program products on storage devices for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.Type: GrantFiled: July 21, 2011Date of Patent: May 1, 2012Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 8131085Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.Type: GrantFiled: July 15, 2011Date of Patent: March 6, 2012Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 8111927Abstract: Systems, methods and computer program products for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. Clip images defined in a received OCR output are classified into a plurality of clusters of clip images. Clip images in each of the plurality of clusters are processed to generate a cluster image for each cluster. Shape differences between the cluster images of a first cluster and a second cluster and between the cluster images of the first cluster and a third cluster are used to determine a level of confidence in one or more first OCR character codes assigned to the first cluster.Type: GrantFiled: May 20, 2010Date of Patent: February 7, 2012Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Publication number: 20120020564Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.Type: ApplicationFiled: July 15, 2011Publication date: January 26, 2012Applicant: GOOGLE INC.Inventors: Luc Vincent, Raymond W. Smith
-
Publication number: 20120008865Abstract: A system and method is provided for automatically recognizing building numbers in street level images. In one aspect, a processor selects a street level image that is likely to be near an address of interest. The processor identifies those portions of the image that are visually similar to street numbers, and then extracts the numeric values of the characters displayed in such portions. If an extracted value corresponds with the building number of the address of interest such as being substantially equal to the address of interest, the extracted value and the image portion are displayed to a human operator. The human operator confirms, by looking at the image portion, whether the image portion appears to be a building number that matches the extracted value. If so, the processor stores a value that associates that building number with the street level image.Type: ApplicationFiled: July 12, 2011Publication date: January 12, 2012Applicant: Google Inc.Inventors: Bo Wu, Alessandro Bissacco, Raymond W. Smith, Kong man Cheung, Andrea Frome, Shlomo Urbach
-
Publication number: 20110280483Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.Type: ApplicationFiled: July 21, 2011Publication date: November 17, 2011Applicant: GOOGLE INC.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 7868512Abstract: A motor-generator system with a current control feedback loop for generating electrical energy in stationary, portable, and automotive applications. The generator includes a housing defining an interior space and including a first portion and a second portion; an electric motor assembly positioned within the first portion of the housing, and operationally coupled to a shaft member for selectively rotating the shaft member; an electric generator assembly positioned within the second portion of the housing and operationally coupled to the shaft member for converting mechanical rotation into electrical energy, the electric generator assembly including a current output for supplying electrical current; and a control assembly operationally coupled between the electric generator assembly and the electric motor assembly the control assembly providing a control current to the electric motor assembly for controlling a speed of rotation induced into the shaft member by the electric motor assembly.Type: GrantFiled: May 14, 2009Date of Patent: January 11, 2011Inventor: Raymond W. Smith
-
Publication number: 20100232719Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.Type: ApplicationFiled: May 20, 2010Publication date: September 16, 2010Applicant: GOOGLE INC.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 7697758Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.Type: GrantFiled: September 11, 2006Date of Patent: April 13, 2010Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 7650035Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.Type: GrantFiled: September 11, 2006Date of Patent: January 19, 2010Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith
-
Patent number: 7646921Abstract: Techniques for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process.Type: GrantFiled: September 11, 2006Date of Patent: January 12, 2010Assignee: Google Inc.Inventors: Luc Vincent, Raymond W. Smith