Search

Kishor Barman Phones & Addresses

  • Saratoga, CA
  • 4473 Headen Way, Santa Clara, CA 95054
  • Mountain View, CA

Resumes

Resumes

Kishor Barman Photo 1

Senior Staff Software Engineer

View page
Location:
Santa Clara, CA
Industry:
Internet
Work:
Google
Senior Staff Software Engineer

Google Nov 2017 - Oct 2019
Staff Software Engineer

Google Nov 2013 - Oct 2017
Senior Software Engineer

Qualcomm Research India Sep 2011 - Aug 2013
Senior Engineer

Yahoo Labs Jun 2010 - Aug 2010
Intern
Education:
Tata Institute of Fundamental Research 2006 - 2011
Master of Science, Doctorates, Masters, Doctor of Philosophy, Computer Science, Philosophy
Tata Institute of Fundamental Research, Mumbai 2011
Doctorates, Doctor of Philosophy, Computer Science
Birla Institute of Technology, Mesra 2005
Birla Institute of Technology and Science, Pilani 2001 - 2005
Bachelor of Engineering, Bachelors, Electronics
Cotton College 2001
Cotton College
Solmara Higher Secondary School
Skills:
Machine Learning
Algorithms
Signal Processing
Recommender Systems
Pattern Recognition
Computer Vision
Augmented Reality
C++
Information Theory
Image Processing
C
Probability
Interests:
Machine Learning
Probability
Information Theory
Wireless Communication
Augmented Reality
Languages:
English
Assamese
Hindi
Kishor Barman Photo 2

Kishor Barman

View page
Kishor Barman Photo 3

Kishor Barman

View page
Kishor Barman Photo 4

Kishor Barman

View page

Publications

Us Patents

Processing Text Images With Shadows

View page
US Patent:
20150193667, Jul 9, 2015
Filed:
Jan 8, 2014
Appl. No.:
14/150682
Inventors:
- San Diego CA, US
Pawan Kumar Baheti - Bangalore, IN
Kishor K. Barman - Santa Clara CA, US
Assignee:
QUALCOMM Incorporated - San Diego CA
International Classification:
G06K 9/18
G06T 5/10
G06T 5/00
G06T 5/40
Abstract:
Embodiments disclosed facilitate robust, accurate, and reliable recovery of words and/or characters in the presence of non-uniform lighting and/or shadows. In some embodiments, a method to recover text from image may comprise: expanding a Maximally Stable Extremal Region (MSER) in an image, the neighborhood comprising a plurality of sub-blocks; thresholding a subset of the plurality of sub-blocks in the neighborhood, the subset comprising sub-blocks with text, wherein each sub-block in the subset is thresholded using a corresponding threshold associated with the sub-block; and obtaining a thresholded neighborhood.

Multiple Hypothesis Testing For Word Detection

View page
US Patent:
20150063700, Mar 5, 2015
Filed:
May 2, 2014
Appl. No.:
14/268904
Inventors:
- San Diego CA, US
Kishor Kumar BARMAN - Santa Clara CA, US
Pawan Kumar BAHETI - Bangalore, IN
Assignee:
QUALCOMM Incorporated - San Diego CA
International Classification:
G06K 9/18
US Classification:
382182
Abstract:
Embodiments disclosed pertain to Optical Character Recognition using Multiple Hypothesis Testing based techniques on images occurring in a variety of settings, including images captured by mobile stations. In some embodiments, a set of bifurcation points for a character cluster in an image may be determined. The character cluster may comprise non-uniformly spaced text or closely spaced text. A plurality of hypotheses may be determined for the character cluster, where each hypothesis is based on a subset of the bifurcation points and comprises a set of words generated from the character cluster. A plurality of scores corresponding to the plurality of hypotheses may be determined, where each score corresponds to a hypothesis, and a hypothesis may be selected from among the plurality of hypotheses based on a score associated with the selected hypothesis.
Kishor Kumar Barman from Saratoga, CA Get Report