Visitors to the Information Initiative at Duke

Abstract

Approach: Prof. Jean-Michel Morel- Prof. Morel is a worldwide leader in image processing, in particular image reconstruction; see https://sites.google.com/site/jeanmichelmorelcmlaenscachan/. Jean-Michel Morel leads a team of 20 researchers and coordinates 20 more on the mathematical analysis of image processing and the invention of new algorithms. This team collaborates with French Space Agency for the design of Earth observation satellites (SPOT5, Pleiades, OTOS). The image denoising algorithms co-invented by JMM are implemented in more than 300 million camera phones by DxO Labs, a world leader in software and hardware for cameras. In 2011 JMM founded Image Processing on Line (www.ipol.im), the first journal publishing reproducible algorithms in online executable articles. IPOL has collaborators in 15 universities and its public archives contain 120000 online experiments. JMM’s recent awards: 2010 Clay Scholar in Residence, European Research Council advanced grant 2010, Grand Prix INRIA – French Academy of Science 2013. Prof. Morel will visit Duke University for one month during the Summer of 2015. During this visit he will work on basic research challenges in image and video analysis, including low-light imaging and the incorporation of learning frameworks in image reconstruction and analysis. During this month, Prof. Morel will interact with members of iiD and open new collaborations between his group and iiD. Prof. Alex Bronstein- His main research interests are theoretical and computational methods in metric geometry and their application to problems in computer vision, pattern recognition, shape analysis, computer graphics, image processing, and machine learning (http://www.cs.technion.ac.il/~bron/). He has authored over 100 publications in leading journals and conferences, over a dozen of patents and patent applications, and the book Numerical geometry of non-rigid shapes (published by Springer). Alex Bronstein is the alumnus of the Technion Excellence Program and the Academy of Achievement, and a member of the IEEE. Prof. Bronstein will visit Duke during the Fall or Spring of 2015, for a period of approximately 3 months. During this time he will work on basic research challenges regarding novel image and video acquisition technologies. In particular, with Prof. Bronstein being the core developer of the new Intel RealSense 3D camera, he will study new directions on research and applications in a world where 3D acquisition becomes cheap and ubiquitous. This includes the use of 3D for human analysis (expression, gaze, etc.), and group behavior analysis. In addition, he plans to investigate fast image and video reconstruction from dense binary cameras, where the sensors only produce binary patters (the incoming light passed a threshold). Lastly, he will study the theory behind deep learning algorithms and potential alternatives such as random forests.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 12, 2016
Source ID
N000141512334

Entities

People

  • Guillermo Sapiro

Organizations

  • Duke University
  • Office of Naval Research
  • United States Navy

Tags

Readers

  • Computer Vision.
  • Military History
  • Research Science/Academic Research

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • Space