Multi-Resolution Intrinsic Texture Geometry-Based Local Binary Pattern for Texture Classification

Creative Commons License

ALPASLAN N., Hanbay K.

IEEE ACCESS, vol.8, pp.54415-54430, 2020 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 8
  • Publication Date: 2020
  • Doi Number: 10.1109/access.2020.2981720
  • Journal Name: IEEE ACCESS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Page Numbers: pp.54415-54430
  • Keywords: Hessian matrix, feature extraction, local binary patterns, texture classification, IMAGE RETRIEVAL, NUMBER PATTERN, COLOR, FEATURES, MODEL, FACE, DESCRIPTORS, RECOGNITION, REPRESENTATION, COOCCURRENCE
  • Inonu University Affiliated: No

Abstract

In this paper, we propose a new hybrid Local Binary Pattern (LBP) based on Hessian matrix and Attractive Center-Symmetric LBP (ACS-LBP), called Hess-ACS-LBP.d The Hessian matrix provides the directional derivative information of different texture regions, while ACS-LBP reveals the local texture features efficiently.d To obtain the macro- and micro-structure textural changes, Hessian matrix is calculated in a multiscale schema.d Multiscale Hessian matrix presents the intrinsic local geometry of the texture changes.d The magnitude information of the Hessian matrix is used in the ACS-LBP method.d A cross-scale joint coding strategy is used to construct Hess-ACS-LBP descriptor.d Finally, histogram concatenation is carried out.d Extensive experiments on eight texture databases of CUReT, USPTex, KTH-TIPS2b, MondialMarmi, OuTeX TC_00013, XU HR, ALOT and STex validate the efficiency of the proposed method.d The proposed Hess-ACS-LBP method achieves about 20% improvement over the original LBP method and 1%-11% improvement over the other state-of-the-art hand-crafted LBP methods in terms of classification accuracy.d Besides, the experimental results show that the proposed method achieves up to 32% better results than the state-of-the-art deep learning based methods.d Especially, the performance of the proposed method on ALOT and STex datasets containing many classes is remarkable.