[1]张磊,陈昊,王岩松,等.自适应权重联合多尺度LBPV2纹理分类方法[J].应用科技,2019,46(02):25-29.[doi:10.11991/yykj.201809006]
 ZHANG Lei,CHEN Hao,WANG Yansong,et al.A adaptive weight joint multi-scale LBPV2 for texture classification[J].Applied science and technology,2019,46(02):25-29.[doi:10.11991/yykj.201809006]
点击复制

自适应权重联合多尺度LBPV2纹理分类方法(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第46卷
期数:
2019年02期
页码:
25-29
栏目:
现代电子技术
出版日期:
2019-03-05

文章信息/Info

Title:
A adaptive weight joint multi-scale LBPV2 for texture classification
作者:
张磊1 陈昊2 王岩松3 李一兵1
1. 哈尔滨工程大学 信息与通信工程学院, 黑龙江 哈尔滨 150001;
2. 南卡罗莱纳州立大学 电子工程学系, 南卡罗莱纳州 哥伦比亚 29204;
3. 国家无线电监测中心 上海监测站, 上海 201419
Author(s):
ZHANG Lei1 CHEN Hao2 WANG Yansong3 LI Yibing1
1. College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China;
2. Department of Electronic Engineering, University of South Carolina, Columbia SC 29204, USA;
3. National Radio Monitoring Center, Shanghai Monitoring Station, Shanghai 201419, China
关键词:
局部二值模式|纹理分类|自适应权重|联合多尺度方案|特征提取|局部方差|统计直方图|纹理数据集
Keywords:
local binary pattern|texture classification|adaptive weight|joint multi-scale scheme|feature extraction|local variance|histogram|texture database
分类号:
TN911.73
DOI:
10.11991/yykj.201809006
文献标志码:
A
摘要:
传统的局部二值模式仅局限于局部纹理信息的提取,忽略了全局纹理信息的表达,造成最终的纹理分类效果并不理想。为了解决以上问题,借鉴局部二值模式方差(LBPV)的优势,在此基础上提出了一种新的基于自适应权重联合多尺度LBPV2的纹理图像分类方法。该方法将方差平方作为直方图累积权重取代原来的方差权重,并采用自适应权重联合多尺度方案来实现多尺度纹理信息提取,进一步提升了纹理图像描述子的分类性能。在国际公认的Outex纹理数据集上的仿真实验表明,提出的这种新的基于自适应权重联合多尺度LBPV2的纹理图像分类方法能够实现纹理分类性能的显著改善。
Abstract:
Local binary pattern (LBP) has been widely used in texture classification, however, traditional local binary pattern is limited in extracting local texture information, and it loses sight of the representation of global texture information, which make the texture classification task not doing well. In order to solve this problem, by taking advantage of local binary pattern variance (LBPV), this paper proposes a new texture image classification method based on the adaptive weight joint multi-scale LBPV2. In this method, it considers the square of variance as histogram cumulative weight instead of traditional variance weight, and it also uses the adaptive weight joint multi-scale scheme to extract the multi-scale texture information, thereby the texture classification performance is further improved. The simulation experiments conducted on popular Outex benchmark texture database indicate that the proposed adaptive weight joint multi-scale LBPV2(AWJLBPV2) can greatly improve the texture classification performance.

参考文献/References:

[1] WOZNIAK M, POLAP D. Object detection and recognition via clustered features[J]. Neurocomputing, 2018, 320:76-84.
[2] SARMA J N, SHARMA S. Neotectonic activity of the Bomdila Fault in northeastern India from geomorphological evidences using remote sensing and GIS[J]. Journal of earth system science, 2018, 127(8):1-9.
[3] LI Ying, KONG Xiangwei, FU Haian, et al. Aggregating hierarchical binary activations for image retrieval[J]. Neurocomputing, 2018, 314:65-77.
[4] AGARWAL M, SINGHAL A, LALL B. 3D local ternary co-occurrence patterns for natural, texture, face and bio medical image retrieval[J]. Neurocomputing, 2018, 313:333-345.
[5] OJALA T, PIETIKÄINEN M, MÄENPÄÄ T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE transactions on pattern analysis and machine intelligence, 2002, 24(7):971-987.
[6] LIAO S, LAW M W K, CHUNG A C S. Dominant local binary patterns for texture classification[J]. IEEE transactions on image processing, 2009, 18(5):1107-1118.
[7] GUO Zhenhua, ZHANG Lei, ZHANG D. Rotation invariant texture classification using LBP variance (LBPV) with global matching[J]. Pattern recognition, 2010, 43(3):706-719.
[8] GUO Zhenhua, ZHANG Lei, Zhang D. A completed modeling of local binary pattern operator for texture classification[J]. IEEE transactions on image processing, 2010, 19(6):1657-1663.
[9] LIU Li, ZHAO Lingjun, LONG Yunli, et al. Extended local binary patterns for texture classification[J]. Image and vision computing, 2012, 30(2):86-99.
[10] WANG Kai, BICHOT C, ZHU Chao, et al. Pixel to patch sampling structure and local neighboring intensity relationship patterns for texture classification[J]. IEEE signal processing letters, 2013, 20(9):853-856.
[11] WU Xiaosheng, SUN Junding. Joint-scale LBP:a new feature descriptor for texture classification[J]. The visual computer, 2017, 33(3):317-329.
[12] ZHAO Yang, JIA Wei, HU Rongxiang, et al. Completed robust local binary pattern for texture classification[J]. Neurocomputing, 2013, 106:68-76.
[13] SONG Kechen, YAN Yunhui, ZHAO Yongjie, et al. Adjacent evaluation of local binary pattern for texture classification[J]. Journal of visual communication and image representation, 2015, 33:323-339.

备注/Memo

备注/Memo:
收稿日期:2018-09-06。
基金项目:国家自然科学基金项目(51809056)
作者简介:张磊,男,硕士研究生;李一兵,男,教授,博士生导师
通讯作者:王岩松,E-mail:wangyansong0451@163.com
更新日期/Last Update: 2019-03-06