Skip navigation

Energy Conservation by Adaptive Feature Loading for Mobile Content-based Image Retrieval

Event Date: September 24, 2008
Speaker: Karthik Kumar
Speaker Affiliation: ECE/Computer Engineering
Sponsor: Computer Engineering Student Seminar Series
Time: 12:00 - 1:00 PM
Location: EE 317
Priority: No
College Calendar: Show

We present an adaptive loading scheme to save energy for content based image retrieval (CBIR) in a mobile system. In CBIR, images are represented and compared by high-dimensional vectors called features. Loading these features into memory and comparing them consumes a significant amount of energy. Our method adaptively reduces the features to be loaded into memory for each query image. The reduction is achieved by estimating the difficulty of the query and by reusing cached features in memory for subsequent queries. We implement our method on a PDA and obtain overall energy reduction of 61.3% compared with an existing CBIR implementation.

This work was recently presented at the ACM/IEEE International Symposium on Lower Power Electronics and Design (ISLPED) held in Bangalore, India from August 11 - 13, 2008.



Karthik Kumar is a first year Ph.D. student in the School of ECE working on energy conservation for mobile systems with Prof. Yung-Hsiang Lu. He obtained an M.S. degree in August 2008 working on "Energy Conservation for Mobile Content-based Image Retrieval".