Please provide your feedback about the website at feedback@apc.iisc.ernet.in
Location: Auditorium, ECE MP Building
ECE Faculty Colloquium Series
Speaker : Rajiv Soundararajan, Dept. of ECE
Date : Friday, 29 March 2019
Time : 4pm (coffee served at 3:45pm)
Venue : MP auditorium, Dept. of ECE
Title : Improving low light photography through joint contrast enhancement and denoising
Abstract: Enhancing details in low light images is of great interest in consumer electronics such as smartphones and in surveillance applications. Existing contrast enhancement algorithms suffer from the problem of noise amplification. Further, denoising algorithms for post processing lead to loss of details. In this talk, we look at the problem of joint contrast enhancement and denoising to overcome the limitations of current algorithms. We discuss two approaches to solving this problem. In the first approach, we devise statistical models of low light natural images in the band pass domain and use such models for joint contrast enhancement and denoising. We will then discuss our initial attempts at the alternate approach of using deep convolutional neural networks to enhance low light images while controlling noise amplification. While we evaluate our algorithms on low light image databases that have been released recently, we will also talk about a new low light image dataset developed here at IISc.
Bio : Rajiv Soundararajan received the B. E. degree in Electrical and Electronics Engineering from Birla Institute of Technology and Science (BITS), Pilani, India in 2006. He received the M. S. and Ph. D. degrees in Electrical and Computer Engineering from The University of Texas at Austin, USA in 2008 and 2012 respectively. Between 2012 and 2015, he was with Qualcomm Research India, Bangalore. He is currently an Assistant Professor at the Indian Institute of Science, Bangalore. He received the 2016 IEEE Circuits and Systems for Video Technology Best Paper Award and the 2017 IEEE Signal Processing Letters Best Paper Award. His research interests are broadly in image and video signal processing, information theory, computer vision and machine learning.
