Click here to register for the workshops.

Mathworks Image Processing Recipes in MATLAB

Presenter: Spandan Tiwari, MathWorks Development

Sunday, September 15, 2013 -- 14:00 to 15:30
Signing up for this workshop is required.

This session is aimed at demonstrating some of the lesser known, but practically useful, workflows and functionality for image processing in MATLAB. Attendees will learn a variety of intermediate and advanced MATLAB functionality and programming techniques that will be useful in writing fast and maintainable image processing code, and communicating the results effectively. Even experienced MATLAB users will come away with something new and useful. This session will include topics such as:

  1. Computational tips and tricks for non-linear filtering
  2. Fast block processing
  3. Fast computation using GPUs
  4. Custom spatial transformations
  5. Publishing results using MATLAB


Spandan Tiwari is a Senior Image Processing Engineer at Mathworks since 2010. At Mathworks, he is with the Image Processing Toolbox where he leads the effort to design and develop functionality based on advanced image processing algorithms intended for use by scientists and engineers. Prior to Mathworks, he was with Migma Systems Inc. where he developed advanced target detection and image understanding algorithms for aerial and ground-based imagery, and computer vision algorithms for monitoring pedestrian and vehicular traffic. His research interests are in the areas of non-linear image filtering, stereo-vision, automatic target recognition, graph-based and level-set methods for image processing, and machine learning. He holds Masters and PhD, both in Electrical Engineering, from Missouri S&T (formerly University of Missouri - Rolla). He is a member of IEEE Signal Processing Society.

Google: Introducing VP9: The next generation open-source video codec

Presenter: Debargha Mukherjee

Monday, September 16, 2013 -- 18:15 to 19:00
Signing up for this workshop is recommended, but not required.

Google has recently finalized a next generation open-source video codec called VP9, as part of the libvpx repository of the WebM project . Starting from the VP8 video codec released by Google in 2010 as the baseline, many enhancements and new tools were added, resulting in the next-generation bit-stream VP9 that was finalized in June 2013. The open-source project has since moved to the next phase - namely efficient implementation of the encoder and decoder for various use-cases. The workshop will introduce attendees to the coding tools included in VP9 along with the rationale for their inclusion. Coding results comparing VP9 to other state-of-the-art video codecs - H.264/AVC and HEVC - on standard test sets will also be provided. Further, the workshop will provide pointers on how interested parties can be involved with the WebM project and contribute either to the master VP9 branch or a divergent experimental branch that can hopefully become a future-generation codec.


Debargha Mukherjee received the MS and PhD degrees in ECE from the University of California Santa Barbara in 1995 and 1999, respectively. Between 1999 and 2010 he was in Hewlett Packard Laboratories conducting research on video and image coding and processing. Since 2010 he has been with Google Inc., where he is currently involved with open-source video codec development. Prior to that he was responsible for video quality control and 2D to 3D conversion on YouTube. Debargha's interests are in signal/image processing, image and video compression, and information theory. He has authored/co-authored more than 75 papers on these topics, and holds more than 20 US patents, with several more pending. He was a student paper award winner at IEEE ICIP in 1998, and a keynote speaker at the SPIE Stereoscopic Displays and Applications conference, and the CVPR 3D Cinematography workshop, both in 2012, to talk about YouTube's 2d to 3D conversion service. He currently serves as Associate Editors of the IEEE Transactions on Image Processing, and the SPIE Journal of Electronic Imaging.