Speaker: Professor Dipti Prasad Mukherjee, Indian Statistical Institute, Kolkata
One of the main objectives of Computer Vision is to interpret the content of image and video. To interpret image content, one of the major targets is to build a model based on a known set of features derived from image and video. The designed model is then used to generate inference about the unseen image or video. We will present a set of machine learning techniques that help train and test an image understanding system. An attempt will be made to understand the model from the basics.
Dipti Prasad Mukherjee is a Professor at the Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata. His primary research interest is in Computer Vision, Image Processing and Computer Graphics. He has written two books on Computer Graphics, edited seven books and authored more than a hundred peer-reviewed research papers. He had held visiting faculty positions at the Oklahoma State University (1998-99), University of Virginia (2002, 2013) and Alcorn State University (2011), USA and the University of Alberta (2006, 2007, 2008, 2009), Canada. Prior to this, Dr Mukherjee is the recipient of the pre-doctoral UNDP fellowship at the Robotics Research Group, University of Oxford (1992), U.K., and the UNESCO-CIMPA fellowship to INRIA (1991, 1993, 1995), France and to ICTP (2000) Italy. In 2010, he had received Japan Society for Promotion of Science (JSPS) Invitation fellowship to the Department of Radiology, Graduate School of Medicine, Osaka University, Japan. He is currently serving as Associate Editor to IEEE Transactions on Image Processing, IET Image Processing, and SADHANA, Springer journal of Indian Academy of Sciences. He is a fellow of the Institution of Engineers (India) and the Computer Society of India.