Patents by Inventor Shashidhar R. Yellareddy
Shashidhar R. Yellareddy 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: 10402702Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: GrantFiled: April 19, 2018Date of Patent: September 3, 2019Assignee: International Business Machines CorporationInventors: Somnath Asati, Soma Shekar Naganna, Abhishek Seth, Vishal Tomar, Shashidhar R. Yellareddy
-
Patent number: 10395146Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: GrantFiled: April 19, 2018Date of Patent: August 27, 2019Assignee: International Business Machines CorporationInventors: Somnath Asati, Soma Shekar Naganna, Abhishek Seth, Vishal Tomar, Shashidhar R. Yellareddy
-
Publication number: 20180239993Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: ApplicationFiled: April 19, 2018Publication date: August 23, 2018Inventors: Somnath ASATI, Soma Shekar NAGANNA, Abhishek SETH, Vishal TOMAR, Shashidhar R. YELLAREDDY
-
Publication number: 20180239994Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: ApplicationFiled: April 19, 2018Publication date: August 23, 2018Inventors: Somnath ASATI, Soma Shekar NAGANNA, Abhishek SETH, Vishal TOMAR, Shashidhar R. YELLAREDDY
-
Patent number: 10026022Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: GrantFiled: September 8, 2017Date of Patent: July 17, 2018Assignee: International Business Machines CorporationInventors: Somnath Asati, Soma Shekar Naganna, Abhishek Seth, Vishal Tomar, Shashidhar R. Yellareddy
-
Patent number: 9996773Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: GrantFiled: August 4, 2016Date of Patent: June 12, 2018Assignee: International Business Machines CorporationInventors: Somnath Asati, Soma Shekar Naganna, Abhishek Seth, Vishal Tomar, Shashidhar R. Yellareddy
-
Publication number: 20180039869Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: ApplicationFiled: September 8, 2017Publication date: February 8, 2018Inventors: Somnath ASATI, Soma Shekar NAGANNA, Abhishek SETH, Vishal TOMAR, Shashidhar R. YELLAREDDY
-
Publication number: 20180039868Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.Type: ApplicationFiled: August 4, 2016Publication date: February 8, 2018Inventors: Somnath ASATI, Soma Shekar NAGANNA, Abhishek SETH, Vishal TOMAR, Shashidhar R. YELLAREDDY
-
Patent number: 9529830Abstract: A computer-implemented method includes receiving a column-oriented table comprising data for a column family, wherein the data for the column family comprises column names and corresponding column values, receiving a set of anonymous column names for the column family, receiving a set of synonymous column names for the column family, determining a weighting for each column name that is not an anonymous column name based on the count or frequency of occurrence of the column name and the synonymous column names within the column-oriented table, and processing the column-oriented table with a probabilistic matching engine using the weighting for each column name. A corresponding computer program product and computer system are also disclosed herein.Type: GrantFiled: January 28, 2016Date of Patent: December 27, 2016Assignee: International Business Machines CorporationInventors: Bhavani K. Eshwar, Soma Shekar Naganna, Umasuthan Ramakrishnan, Shashidhar R. Yellareddy