Discriminative Basis Selection using Non-negative Matrix Factorization

Aruna Jammalamadaka, Swapna Joshi, S. Karthikeyan, B.S. Manjunath
Dept. of Electrical and Computer Engineering, University of California, Santa Barbara CA 93106
{arunaj, swapnaj, karthikeyan, manj} [at] ece.ucsb.edu


Non-negative matrix factorization (NMF) has proven to be useful in image classification applications such as face recognition. We propose a novel discriminative basis selection method for classification of image categories based on the popular term frequency-inverse document frequency (TF-IDF) weight used in information retrieval. We extend the algorithm to incorporate color, and overcome the drawbacks of using unaligned images. Our method is able to choose visually significant bases which best discriminate between categories and thus prune the classification space to increase correct classifications. We apply our technique to ETH80, a standard image classification benchmark dataset. Our results show that our algorithm outperforms other state-of-the-art techniques.
[PDF] [BibTex]
Aruna Jammalamadaka, Swapna Joshi, S. Karthikeyan, B.S. Manjunath,
IEEE International Conference on Pattern Recognition, Aug. 2010.
Node ID: 549 , DB ID: 358 , Lab: VRL , Target: Conference
Subject: [Object-Based Retrieval] « Look up more