Research Interests: Deep Learning, Machine Learning, Pattern Recognition, Image Processing, Computer Vision, Computer Graphics
- Flipkart, July 9, 2015 - present
Principal Scientist & Head of Image Sciences - leading Computer Vision and Deep Learning projects at Flipkart. Some press clips: Times Of India, The Economic Times, Bloomberg, Business Standard, NextBigWhat, The Hindu. In particular,
- Deep Learning based Visually Similar recommendations for Flipkart: A new Convolutional Neural Net (CNN) architecture for visual feature embeddings. Recommendations are made from k Nearest Neighbors of the embedding for the product that user is browsing. Here is video for my slashn talk on this. Here are slides for my Indian Institute of Science, Bangalore and Indian Statistical Institute, Kolkata talks.
- Region CNN based e-commerce product localization on wild images: Identifying Flipkart apparels similar to the ones worn by models/celebrities/friends in wild images.
- Visual Semantic Embeddings for e-commerce Products: Identifying product embeddings.
- Neural Network Retail Modeling: in progress.
- Google, Sep 12 2005 - July 6, 2015
Uber Technology Leader & Staff Software Engineer - leading image processing, computer vision related projects. In particular,
- 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".
List of Selected Patents and Publications
- "Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce", D. Shankar, Sujay S., Ananya H., Krishnendu Chaudhury, Asian Conference on Computer Vision, ACCV 2016, Taipei (under review).
- "Handheld or Wearable Document Scanner for Google", Krishnendu Chaudhury, Lu Chen, David Petrou, Blaise Aguerra, GP-22700-00-US, Google Patent Application.
- "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.
- "Segmenting Printed Media Pages into Articles", Krishnendu Chaudhury, A. Jain & S. Thirthala, 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.
- “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