Learning completed discriminative local features for texture classification | |
Zhang, Zhong1; Liu, Shuang1; Mei, Xing2; Xiao, Baihua3; Zheng, Liang4 | |
发表期刊 | PATTERN RECOGNITION |
2017-07-01 | |
卷号 | 67页码:263-275 |
文章类型 | Article |
摘要 | Local binary patterns (LBP) and its variants have shown great potentials in texture classification tasks. LBP-like texture classification methods usually follow a two-step feature extraction process: in the first pattern encoding step, the local structure information around each pixel is encoded into a binary string; in the second histogram accumulation step, the binary strings are accumulated into a histogram as the feature vector of a texture image. The performances of these classification methods are closely related to the distinctiveness of the feature vectors. In this paper, we propose a novel feature representation method, namely Completed Discriminative Local Features (CDLF), for texture classification. The proposed CDLF improves the distinctiveness of LBP-like feature vectors in two aspects: in the pattern encoding stage, we learn a transformation matrix using labeled data, which significantly increases the discrimination power of the encoded binary strings; in the histogram accumulation step, we use an adaptive weight strategy to consider the contributions of pixels in different regions. The experimental results on three challenging texture databases demonstrate that the proposed CDLF achieves significantly better results than previous LBP-like feature representation methods for texture classification tasks. (C) 2017 Elsevier Ltd. All rights reserved. |
关键词 | Texture Classification Discriminative Learning Local Binary Patterns Adaptive Histogram Accumulation |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1016/j.patcog.2017.02.021 |
关键词[WOS] | ROTATION-INVARIANT FEATURES ; BINARY PATTERNS ; IMAGE CLASSIFICATION ; FACE RECOGNITION ; RADON-TRANSFORM ; RANDOM-FIELDS ; GRAY-SCALE ; SEGMENTATION ; RETRIEVAL ; FILTERS |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | National Natural Science Foundation of China(61401309 ; Natural Science Foundation of Tianjin(15JCQNJC01700) ; Doctoral Fund of Tianjin Normal University(5RL134 ; Open Projects Program of National Laboratory of Pattern Recognition(201700001) ; 61501327 ; 52X61405) ; 61401310) |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000399520700022 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/15091 |
专题 | 复杂系统管理与控制国家重点实验室_影像分析与机器视觉 |
作者单位 | 1.Tianjin Normal Univ, Tianjin Key Lab Wireless Mobile Commun & Power Tr, Tianjin 300387, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Intelligent Control Co, Beijing 100190, Peoples R China 4.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 2007, Australia |
推荐引用方式 GB/T 7714 | Zhang, Zhong,Liu, Shuang,Mei, Xing,et al. Learning completed discriminative local features for texture classification[J]. PATTERN RECOGNITION,2017,67:263-275. |
APA | Zhang, Zhong,Liu, Shuang,Mei, Xing,Xiao, Baihua,&Zheng, Liang.(2017).Learning completed discriminative local features for texture classification.PATTERN RECOGNITION,67,263-275. |
MLA | Zhang, Zhong,et al."Learning completed discriminative local features for texture classification".PATTERN RECOGNITION 67(2017):263-275. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论