Orientation selectivity-based structure for texture classification

Jinjian Wu; Weisi Lin; Guangming Shi; Yazhong Zhang; Liu Lu

doi:10.1117/12.2071438

Translator Disclaimer

29 October 2014 Orientation selectivity based structure for texture classification

Jinjian Wu, Weisi Lin, Guangming Shi, Yazhong Zhang, Liu Lu

Author Affiliations +

Proceedings Volume 9273, Optoelectronic Imaging and Multimedia Technology III; 92732M (2014) https://doi.org/10.1117/12.2071438
Event: SPIE/COS Photonics Asia, 2014, Beijing, China

Abstract

Local structure, e.g., local binary pattern (LBP), is widely used in texture classification. However, LBP is too sensitive to disturbance. In this paper, we introduce a novel structure for texture classification. Researches on cognitive neuroscience indicate that the primary visual cortex presents remarkable orientation selectivity for visual information extraction. Inspired by this, we investigate the orientation similarities among neighbor pixels, and propose an orientation selectivity based pattern for local structure description. Experimental results on texture classification demonstrate that the proposed structure descriptor is quite robust to disturbance.

Citation Download Citation

Jinjian Wu, Weisi Lin, Guangming Shi, Yazhong Zhang, and Liu Lu "Orientation selectivity based structure for texture classification", Proc. SPIE 9273, Optoelectronic Imaging and Multimedia Technology III, 92732M (29 October 2014); https://doi.org/10.1117/12.2071438

ACCESS THE FULL ARTICLE