DMCA
Learning How to Extract Rotation-Invariant and Scale-Invariant Features from Texture Images (2007)
| Citations: | 6 - 4 self |
BibTeX
@MISC{Montoya-zegarra07learninghow,
author = {Javier A. Montoya-zegarra and João Paulo Papa and Neucimar J. Leite and Ricardo Da Silva Torres and Re X. Falcão},
title = {Learning How to Extract Rotation-Invariant and Scale-Invariant Features from Texture Images},
year = {2007}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract — Learning how to extract texture features from noncontrolled environments characterized by distorted images is a still-open task. By using a new rotation-invariant and scaleinvariant image descriptor based on Steerable Pyramid Decomposition, and a novel multi-class recognition method based on Optimum-Path Forest, a new texture recognition system is proposed. By combining the discriminating power of our image descriptor and classifier, our system uses small size feature vectors to characterize texture images without compromising overall classification rates. State-of-the-art recognition results are further presented on the Brodatz dataset. High classification rates demonstrate the superiority of the proposed system. Index Terms — texture recognition, machine learning, image feature extraction, steerable pyramid decomposition, optimumpath forest classifier. Fig. 1. directional vs. nondirectional visual cues. Fig. 3. fine vs. coarse visual cues. Fig. 2. smooth vs. rough visual cues. Fig. 4. uniform vs. non-uniform visual cues. I.
Keyphrases
texture image scale-invariant feature steerable pyramid decomposition still-open task brodatz dataset index term texture recognition coarse visual cue image feature extraction directional v non-uniform visual cue machine learning distorted image smooth v small size feature vector overall classification rate fine v image descriptor noncontrolled environment nondirectional visual cue high classification rate novel multi-class recognition method texture feature state-of-the-art recognition result scaleinvariant image descriptor new texture recognition system rough visual cue uniform v abstract learning optimum-path forest
