Fusing DTCWT and LBP Based Features for Rotation, Illumination and Scale Invariant Texture Classification

IEEE Access

Guowei Yang¹  Peng Yang¹  Fanlong Zhang¹ 

[1] School of Technology, Nanjing Audit University, Nanjing, China;

关键词: Texture feature extraction;    dual-tree complex wavelet transform;    local binary pattern;    texture classification;   

DOI  :  10.1109/ACCESS.2018.2797072

来源: DOAJ

【 摘 要 】

Classification of texture images with different orientation, illumination, and scale changes is a challenging problem in computer vision and pattern recognition. This paper proposes two descriptors and uses them jointly to fulfill such task. One can obtain an image pyramid by applying dual-tree complex wavelet transform (DTCWT) on the original image, and generate local binary patterns (LBP) in DTCWT domain, called LBPDTCWT, as local texture features. Moreover, log-polar (LP) transform is applied on the original image, and the energies of DTCWT coefficients on detail subbands of the LP image, called LPDTCWTE, are taken as global texture features. We fuse the two kinds of features for texture classification, and the experimental results on benchmark data sets show that our proposed method can achieve better performance than other the state-of-the-art methods.

【 授权许可】

Unknown