中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
A Novel Adaptively Binarizing Magnitude Vector Method in Local Binary Pattern Based Framework for Texture Classification

文献类型：期刊论文

作者Hu, Shiqi3,5,6; Pan, Zhibin3,6; Dong, Jing4; Ren, Xincheng1,2
刊名IEEE SIGNAL PROCESSING LETTERS
出版日期2022
卷号29页码:852-856
关键词Local binary pattern (LBP) adaptively binarizing magnitude vector (ABMV) threshold average vector threshold texture classification
ISSN号1070-9908
DOI10.1109/LSP.2022.3158199
通讯作者Pan, Zhibin(zbpan@mail.xjtu.edu.cn)
英文摘要Local Binary Pattern (LBP) based framework only uses a scalar threshold to binarize all magnitude vectors in P different directions around each center pixel of a texture image. Hence, the original LBP-based framework, in fact, can not precisely extract different magnitude features in P different directions around each center pixel. Furthermore, the value of magnitude vectors can have dramatic changes from coarse areas to flat areas in the same texture image. Therefore, using a scalar threshold calculated from whole texture image can not precisely binarize all magnitude vectors in coarse areas and flat areas simultaneously. To overcome these two drawbacks, we propose a novel adaptively binarizing magnitude vector (ABMV) method. Firstly, we adaptively calculate the average vector threshold ($)over-right-arrowt(P) with different directional values of all magnitude vectors to replace the scalar threshold/ to binarize the magnitude vectors. The proposed ABMV method can more precisely extract the different magnitude features in P different directions around each center pixel. Secondly, we divide the original texture image into smaller sub-images and adaptively extract their average vector threshold from each sub-image separately. Because the correlation of the pixels in the same sub-image is stronger than that in a whole texture image, the ABMV method can more precisely extract different magnitude features from either coarse areas or flat areas. Finally, we introduce the proposed ABMV method into LBP-based framework. Extensive experiments are conducted on five representative texture databases: Outex, UIUC, CUReT, XU_HR and ALOT database. After introducing the ABMV method into CLBP, CLBC, BRINT and CJIBP, the classification accuracy and the robustness to noise of these methods can be significantly improved.
WOS关键词ROTATION-INVARIANT
资助项目National Natural Science Foundation of China[U1903213] ; Key Science and Technology Program of Shaanxi Province[2020GY-005] ; Open Project of Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data[IPBED8] ; Zhejiang Provincial Commonweal Project[LGF21F030002] ; Open Project of the National Laboratory of Pattern Recognition[202100033]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000777324800003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Key Science and Technology Program of Shaanxi Province ; Open Project of Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data ; Zhejiang Provincial Commonweal Project ; Open Project of the National Laboratory of Pattern Recognition
源URL[http://ir.ia.ac.cn/handle/173211/48243]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Pan, Zhibin
作者单位1.Yanan Univ, Sch Phys & Elect Informat, Yanan 716000, Peoples R China
2.Yanan Univ, Shaanxi Key Lab Intelligent Proc Big Energy Data, Yanan 716000, Peoples R China
3.Xi An Jiao Tong Univ, Fac Elect & Informat Engn, Xian 710049, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
5.AVIC Xian Flight Automat Control Res Inst, Xian 710076, Peoples R China
6.Xi An Jiao Tong Univ, Res Inst Zhejiang Prov, Xian 710049, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Shiqi,Pan, Zhibin,Dong, Jing,et al. A Novel Adaptively Binarizing Magnitude Vector Method in Local Binary Pattern Based Framework for Texture Classification[J]. IEEE SIGNAL PROCESSING LETTERS,2022,29:852-856.
APA Hu, Shiqi,Pan, Zhibin,Dong, Jing,&Ren, Xincheng.(2022).A Novel Adaptively Binarizing Magnitude Vector Method in Local Binary Pattern Based Framework for Texture Classification.IEEE SIGNAL PROCESSING LETTERS,29,852-856.
MLA Hu, Shiqi,et al."A Novel Adaptively Binarizing Magnitude Vector Method in Local Binary Pattern Based Framework for Texture Classification".IEEE SIGNAL PROCESSING LETTERS 29(2022):852-856.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。