Start a hangout
Works at Google
Attended University of Kentucky
Lives in Saratoga California
- University of KentuckyPhD, Computer Science
i can touch the tip of my nose with my tongue
Krishnendu Chaudhury aka Krish Chaudhury
Research Interests: Deep Learning, Machine Learning, Pattern Recognition, Image Processing, Computer Vision, Computer Graphics
- Google, Sep 12 2005 - present
Uber Technology Leader & Staff Software Engineer - leading image processing, computer vision related projects. In particular,
- Google Reasearch (Machine Intelligence group): Leading computer vision and pattern recognition efforts.
- Google Plus Photos: Auto rectification of user photos, Face recognition based image enhancements, state of the art image de-noising, logo detection based image enhancements
- Face Recognition Based Login System: includes a Histogram of Oriented Gradients (HoG) based gaze detector for liveness detection
- WebP image format: Lead the project through its first launch. WebP is a still image format that can result in upto 40% smaller image file-size (vis a vis JPeg) at comparable visual quality. It was launched in Oct 2010, vide Google blogand Chromium blog. Here are some more media stories: (i) Google offers JPEG alternative for faster Web - CNET News (ii) WebP: Google's attempt to change images on the web - Google 24/7 ... (iii) Techmeme: Google offers JPEG alternative for faster Web (Stephen ... (iv) Wikimedia
- Google Newspaper Search: Lead this project from its inception. The initial version of this was launched on Sep 8, 2008. Please refer to Google Blog Bringing history online, one newspaper at a time. Here are some pointers to relevantpress coverage: (i). New York Times (ii). The Guardian (iii) TechCrunch (iv) BBC (v) Economic Times (vi) San Francisco Chronicle and many others. Please see http://news.google.com/archivesearch to check the product.
- OCR for Google Goggles: Developed a Histogram of Oriented Gradients based shape recognizer for Google Goggles.
- Adobe Systems, San Jose, CA, Feb 1996 - Sep 12 2005
Senior Computer Scientist, ATG (Advanced Technology Group), Acrobat Engineering, PostScript Advanced Development.
- Keane Inc, Boca Raton, FL, Dec 1993 - Feb 1996
Senior Consultant (attached to IBM); worked on OS2 Graphics Engine & Presentation Manager
- University of Kentucky, Lexington, KY, Aug 1993 - Dec 1993
Instructor, Dept. of Computer Science (taught Intro to Numerical Analysis, Intro to Data Structures & Algorithms)
- University of Kentucky, Lexington, KY, Aug 1989 - Aug 1993
Research Assistant, Center for Robotics, University of Kentucky (NASA research projects)
- PhD, Computer Science University of Kentucky at Lexington, Lexington, KY, USA
- Dissertation: "Motion Estimation from a sequence of Intensity or Range Images".
- "Handheld or Wearable Document Scanner for Google", Krishnendu Chaudhury, Lu Chen, David Petrou, Blaise Aguerra, GP-22700-00-US, Google Patent Application.
- "Auto-Rectification of User Photos", Krishnendu Chaudhury, Stephen DiVerdi, Sergey Ioffe, proc. of IEEE International Conference on Image Processing, ICIP 2014, Oct 27-30, 2014, Paris.
- "Automatic Rectification of Distortions in images", Krishnendu Chaudhury, Stephen Diverdi, US Patent 9064309.
- "Liveness Detection in Face Recognition based Authentication Systems", Krishnendu Chaudhury, Avani Devarasetty, U.S Patent US8856541.
- “Automatic extraction of character groundtruth data from images”, Alessandro Bissacco, Krishnendu Chaudhury, U. S. Patent 8755595.
- “Google Newspaper Search – Image Processing and Analysis Pipeline”, Krishnendu Chaudhury et al, 10th International Conference on Document Analysis and Recognition, ICDAR 2009, July 26 – 29, Barcelona, Spain (http://www.cvc.uab.es/icdar2009/papers/3725a621.pdf or GoogleNewspaperSearch_ICDAR2009.pdf or ICDAR2009_presentation.ppt).
- "Segmenting Printed Media Pages into Articles", Krishnendu Chaudhury, A. Jain & S. Thirthala, U.S Patent 8290268, Google
- "Identifying a Front Page in Media Material", Krishnendu Chaudhury et al, U.S Patent 8218913, Google
- "Method and Apparatus for Enhancing Object Boundary Precision in Images", Krishnendu Chaudhury, Ashutosh Kulshreshtha, U.S patent 07813582, Google.
- “Digital Image Archiving in Mobile Device System”, Krishnendu Chaudhury, Ashutosh Garg, Arvind Saraf, Prasenjit Phukan, U.S Patent 7986843, Google.
- "Complexity Based Adaptive Tiling for Transparency Flattener", Krish Chaudhury, Dejan Markovic, U.S Patent 7385727, Adobe Systems.
- “A Cubic B Spline Intensity Re-sampling Based Method for Automatic Image Feature Embedding”, Krish Chaudhury, Dejan Markovic, U.S. Patent 7734118, Adobe Systems.
- “Scaling of Raster Images without Edge Blurring”, Krish Chaudhury, Dejan Markovic, U.S. Patent 7817871, Adobe Systems.
- "Author Signature for Legal Purposes", Jim Pravetz, Krish Chaudhury, Sunil Agrawal, U.S. Patent 7774608, Adobe Systems).
- "Document Modification Detection and Prevention", Krish Chaudhury, Jim Pravetz, Sunil Agrawal, U.S. Patent 7735144, Adobe Systems.
- "Document Digest Allowing Selective Changes to a PDF Document", Krish Chaudhury, Jim Pravetz, International Patent, Adobe Systems, PCT/US2004/015116).
- "Dynamic Enabling of Functionality in Electronic Document Readers", Krish Chaudhury, Jim Pravetz, U.S. Patent 7278168, Adobe Systems.
- "Detecting 3D Motion Field from Range Image Sequence", Krishnendu Chaudhury, R. Mehrotra, Cid Srinivasan, IEEE Transactions on Systems, Man, and Cybernetics journal, vol. 29, No. 2, April 1999 (Detecting3DMotionFieldFromRangeImageSequence.pdf).
- "A Trajectory based Computational Model for Optical Flow Computation", Krishnendu Chaudhury, R. Mehrotra, IEEE Transactions on Robotics and Automation journal, pp. 733-741, vol. 11, No. 5, Oct 1995 (TrajectoryBasedOpticalFlow_ChaudhuryMehrotra.pdf).
- "Optical Flow Estimation using Smoothness of Intensity Trajectories", Krishnendu Chaudhury, R. Mehrotra, CVGIP: Image Understanding journal, pp. 230-244, vol. 60, No. 2, September, 1994.
- "Detecting 3D Flow", Krishnendu Chaudhury, R. Mehrotra, International Conference on Robotics and Automation, San Diego, California, May 8-13, 1994.
- Optical Flow from an Extended Frame Sequence, Krishnendu Chaudhury, R. Mehrotra, International Conference on Robotics and Automation, Atlanta, Georgia, May 2-7, 1993.
- A Parallel Algorithm for 3D Point Pattern Matching, Krishnendu Chaudhury, R. Mehrotra, IEEE International Conference on Systems, Man and Cybernetics, Charlottesville, Virginia, Oct. 13-16 1991.
- Loss and Gain of Optical Couplers with Collision Detection for CSMA/CD based LANs, A. Das, Krishnendu Chaudhury, IEEE International Conference on Communication Systems, ICCS-89, Singapore, Oct. 12-16, 1989
- Playing with my daughter, sitting in the kitchen with the whole family
I can defeat my cellphone in kickboxing
deep learning, convolution neural networks, pattern recognition, computer vision, image processing
- Adobe Systems, San Jose1996 - 2005
Mountain View California - Lexington, KY - Calcutta
- https://5499837803091155165-a-1802744773732722657-s-sites.googlegroups.com/site/krishhomepage/Home/Detecting3DMotionFieldFromRangeImageSequence.pdf?attachauth=ANoY7cqjy-HeX6zd2GmpbzjLX_s25L67IQCjnUNLqR9DkyG-CczUfzS_FpMdosREW4v60gpltIWO6ILwuTsPb1v9sYjQXsjSJ241kO-QUT4H7oh_mxMRhLTh2a5Xd80twL81_xg1_cNT-na429wU5rCrOfsagADCHSuSYmbJUB23iIQUG7LpiAKw2YdSuNrTs3Tzx96tJVJH4xDpxD0Xabg11VvX4hJRxMdORyoHGWwYpbyQKBC6WOq1E-kUr2qrGFEbjFQLjUIY&attredirects=0 (current)