Multiscale texture classification using reduced quaternion wavelet transform

Authors: Shan Gai, Guowei Yang, Sheng Zhang

Abstract:
This article proposes a study of the reduced quaternion wavelet transform (RQWT) which has one shiftinvariant magnitude and three angle phases at each scale from digital image analysis application. A new multiscale texture classifier which uses features extracted from the sub-bands of the RQWT decomposition is proposed in the transform domain. The proposed method can achieve a high texture classification rate. The experimental results can demonstrate the robustness of the proposed method and achieve a higher texture classification accuracy rate than a famous wavelet transform based classifier.

Keywords:
Feature extraction
Reduced quaternion wavelet transform
Texture classification

Published in: AEÜ-International Journal of Electronics and Communications (Volume 67, Issue 3, March 2013)

Publisher: Elsevier

ISSN Information: 1434-8411

Multiscale texture classification using reduced quaternion wavelet transform

Bình luận của bạn

*

*

*

*

 Captcha

Gửi bình luận nhập lại