By Topic

Enhancing DPF for near-replica image recognition

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
3 Author(s)
Yan Meng ; Electr. & Comput. Eng. Dept., Univ. of California, Santa Barbara, CA, USA ; E. Chang ; Beitao Li

Dynamic Partial Function (DPF), which dynamically selects a subset of features to measure pairwise image similarity, has been shown to be very effective in near-replica image recognition. DPF, however, suffers from the one-size-fits-all problem: it requires that all pairwise similarity measurements must use the same number of features. We propose methods for enhancing DPF's performance by allowing different numbers of features to be selected in a pairwise manner. Through extensive empirical studies, we show that our three schemes: thresholding, sampling and weighting, and hybrid schemes of these three basic approaches, substantially outperform DPF in near-replica image recognition.

Published in:

Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on  (Volume:2 )

Date of Conference:

18-20 June 2003