In-plane Rotation and Scale Invariant Clustering and Dictionary Learning

Published

June 3, 2013

Author(s)

P J. Phillips, Challa Sastry, Yi-Chen Chen, Vishal M. Patel, Rama Chellappa

Abstract

n this paper, we present an approach that simulta- neously clusters images and learns dictionaries from the clusters. The method learns dictionaries in the Radon transform domain, while clustering in the image domain. The main feature of the proposed approach is that it provides both in-plane rotation and scale invariant clustering, which is useful in numerous applications including Content Based Image Retrieval (CBIR). We demonstrate the effectiveness of our rotation and scale invariant clustering method on a series of CBIR experiments. The experiments are performed on the Smithsonian isolated leaf, Kimia shape, and Brodatz texture datasets. Our method provides both good retrieval performance and greater robustness compared to standard Gabor-based and three state-of-the-art shape-based methods that have similar objectives.

Citation

IEEE Transactions on Image Processing

Volume

22

Issue

6

Pub Type

Journals

Download Paper

Local Download

Citation

Phillips, P. , Sastry, C. , Chen, Y. , Patel, V. and Chellappa, R. (2013), In-plane Rotation and Scale Invariant Clustering and Dictionary Learning, IEEE Transactions on Image Processing, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=913134 (Accessed April 16, 2024)