List of Past Events
Hybrid Neuro-Computer Vision BCI for Rapid Image Retrieval
Dr. Shih-Fu Chang
Monday, October 06, 2014, 12:00pm - 07:00pm
Columbia University, Departments of Electrical Engineering and Computer Science
Human vision system is able to recognize a wide range of targets under challenging conditions, but has limited throughput. Machine vision and automatic content analytics can process images at a high speed, but suffers from inadequate recognition accuracy for general target classes. In this talk, we present a new hybrid vision paradigm to explore and combine the strengths of both systems. A single trial EEG-based brain machine interface (BCI) subsystem is used to detect objects of interest of arbitrary classes from an initial subset of images. The EEG detection outcomes are used as noisy labels to a graph-based semi-supervised learning subsystem to refine and propagate the labels to retrieve relevant images from a much larger pool. The combined strategy is unique in its generality, robustness, and high throughput. It has great potential for advancing the state of the art in image retrieval applications. We will discuss the performance gains of the proposed hybrid system with multiple and diverse image classes over several data sets, including those commonly used in object recognition, remote sensing images, and 3D navigation environment.
(Joint work with Paul Sajda, Eric Pohlmeyer, Dave Jangraw, and Jun Wang)
Bio:
Shih-Fu Chang is the Richard Dicker Professor and Senior Vice Dean of Engineering School at Columbia University. His research has been focused on multimedia retrieval, addressing fundamental issues of content analysis, large-scale indexing, multimodal fusion, and interactive search. His group has developed and deployed several novel image/video search systems, including one of the earliest content-based image search systems, VisualSEEk, a million-scale mobile product search system implementing compact hashing methods, and a new image search paradigm combining brain machine interface and machine vision. His work has been recognized by paper awards and the Technical Achievement Awards of IEEE Signal Processing Society and ACM Special Interest Group on Multimedia.
