A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification
Texture classification algorithms using local binary pattern (LBP) and its variants usually can achieve attractive results. However, the selected rotation invariant structural patterns in numerous LBP variants are not absolutely continuous invariant to any rotation angle. To improve the classificati...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8369056/ |
| _version_ | 1818379626220617728 |
|---|---|
| author | Qiqi Kou Deqiang Cheng Liangliang Chen Kai Zhao |
| author_facet | Qiqi Kou Deqiang Cheng Liangliang Chen Kai Zhao |
| author_sort | Qiqi Kou |
| collection | DOAJ |
| description | Texture classification algorithms using local binary pattern (LBP) and its variants usually can achieve attractive results. However, the selected rotation invariant structural patterns in numerous LBP variants are not absolutely continuous invariant to any rotation angle. To improve the classification effectiveness on this occasion, in this paper, we introduce a robust descriptor based on the principal curvatures (PCs) and rotation invariant version of CLBP_Sign operator in completed LBP (CLBP), namely PC-LBP. Different from the original LBP and many LBP variants, PCs are employed in this paper to represent each local structure information due to their continuous rotation invariance. Simultaneously, both microand macro-structure texture information can also be captured through PCs, which comprise maximum and minimum curvatures. Inspired by the similar coding strategy of the CLBP_Sign operator, a new operator CLBP_PC is developed. By exploiting complementary information resulting from the two operators combination, the final PC-LBP descriptor has the properties of conspicuous rotation invariance, strong discriminativeness, gray scale invariance, needless of pretraining, and high computational efficiency. In addition, to improve the robustness of texture classification with multiresolution, a multiscale sampling approach is designed by adjusting three parameters accordingly. Experimental results demonstrate that the proposed multiresolution PC-LBP approach achieves comparable performance or outperforms a large number of state-of-the-art methods. Impressively, the classification accuracy of the proposed method performed on Outex_TC_00010 test suite is 100%. |
| first_indexed | 2024-12-14T02:05:46Z |
| format | Article |
| id | doaj.art-3010607696304cd69a70fb7a6b07cacc |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T02:05:46Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3010607696304cd69a70fb7a6b07cacc2022-12-21T23:20:53ZengIEEEIEEE Access2169-35362018-01-016306913070110.1109/ACCESS.2018.28420788369056A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture ClassificationQiqi Kou0https://orcid.org/0000-0003-2873-2636Deqiang Cheng1Liangliang Chen2Kai Zhao3School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaTexture classification algorithms using local binary pattern (LBP) and its variants usually can achieve attractive results. However, the selected rotation invariant structural patterns in numerous LBP variants are not absolutely continuous invariant to any rotation angle. To improve the classification effectiveness on this occasion, in this paper, we introduce a robust descriptor based on the principal curvatures (PCs) and rotation invariant version of CLBP_Sign operator in completed LBP (CLBP), namely PC-LBP. Different from the original LBP and many LBP variants, PCs are employed in this paper to represent each local structure information due to their continuous rotation invariance. Simultaneously, both microand macro-structure texture information can also be captured through PCs, which comprise maximum and minimum curvatures. Inspired by the similar coding strategy of the CLBP_Sign operator, a new operator CLBP_PC is developed. By exploiting complementary information resulting from the two operators combination, the final PC-LBP descriptor has the properties of conspicuous rotation invariance, strong discriminativeness, gray scale invariance, needless of pretraining, and high computational efficiency. In addition, to improve the robustness of texture classification with multiresolution, a multiscale sampling approach is designed by adjusting three parameters accordingly. Experimental results demonstrate that the proposed multiresolution PC-LBP approach achieves comparable performance or outperforms a large number of state-of-the-art methods. Impressively, the classification accuracy of the proposed method performed on Outex_TC_00010 test suite is 100%.https://ieeexplore.ieee.org/document/8369056/Texture classificationprincipal curvatureslocal binary pattern (LBP)completed local binary pattern (CLBP) |
| spellingShingle | Qiqi Kou Deqiang Cheng Liangliang Chen Kai Zhao A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification IEEE Access Texture classification principal curvatures local binary pattern (LBP) completed local binary pattern (CLBP) |
| title | A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification |
| title_full | A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification |
| title_fullStr | A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification |
| title_full_unstemmed | A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification |
| title_short | A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification |
| title_sort | multiresolution gray scale and rotation invariant descriptor for texture classification |
| topic | Texture classification principal curvatures local binary pattern (LBP) completed local binary pattern (CLBP) |
| url | https://ieeexplore.ieee.org/document/8369056/ |
| work_keys_str_mv | AT qiqikou amultiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT deqiangcheng amultiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT liangliangchen amultiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT kaizhao amultiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT qiqikou multiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT deqiangcheng multiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT liangliangchen multiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification AT kaizhao multiresolutiongrayscaleandrotationinvariantdescriptorfortextureclassification |