Using global information to refine local patterns for texture representation and classification. (November 2022)

• Record Type: Journal Article
• Authors: Shu, Xin; Pan, Hui; Shi, Jinlong; Song, Xiaoning; Wu, Xiao-Jun
• Is Part Of: Pattern recognition. Volume 131(2022)
• Publication Date: 2022-11
• Subjects: Texture classification -- Texture descriptor -- Texture representation -- Feature pattern refinement -- Local binary pattern; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108843
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: This paper proposes a novel global refined local binary pattern (GRLBP) by analyzing the nature of the distribution of pixel intensity in local neighborhoods. GRLBP consists of two descriptors termed as magnitude refined local sign binary pattern (MRLBP_S) and center refined local magnitude binary pattern (CRLBP_M). MRLBP_S distinguishes local neighborhoods with contrast differences by using global magnitude anchors to refine local sign patterns. CRLBP_M identifies local neighborhoods with gray differences by employing global central gray anchors to refine local magnitude patterns. RLBP has obvious advantages in classification performance, computational complexity, and feature dimension. Abstract: Local binary pattern (LBP) and its variants have been successfully applied in texture feature extraction. However, it is hard for most LBP-based methods to effectively describe and distinguish the local neighborhoods with similar structures (that is, the calculated feature patterns are identical) but different contrasts or grayscales. To alleviate such problems, we propose a novel global refined local binary pattern (GRLBP) by analyzing the nature of pixel intensity distribution in local neighborhoods. GRLBP consists of two descriptors called magnitude refined local sign binary pattern (MRLBP_S) and center refined local magnitude binary pattern (CRLBP_M). MRLBP_S distinguishes local neighborhoods with contrast differences by using global magnitude anchors to refine local sign patterns. And CRLBP_M identifies local neighborhoods with grayscale differences by employing global central grayscale anchors to refine local magnitude patterns. Finally, frequency histograms of MRLBP_S and CRLBP_M from each image are cascaded to generate the GRLBP. Extensive experimental results on seven benchmark texture databases: Outex, CUReT, KTH-TIPS, UMD, UIUC, KTH-T2b, and DTD demonstrate that the proposed GRLBP can represent the detailed information of texture images. Furthermore, compared with state-of-the-art LBP variants, GRLBP has competitive advantages in classification accuracy, feature dimension, and computational complexity, respectively.