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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Texture Classification in Extreme Scale Variations Using GANet

文献类型：期刊论文

作者Chen, Xilin1; Liu, Li4,5; Chen, Jie3,4; Zhao, Guoying4; Fieguth, Paul2; Pietikainen, Matti4
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2019-08-01
卷号28期号:8页码:3910-3922
关键词Texture descriptors rotation invariance local binary pattern (LBP) feature extraction texture analysis
ISSN号1057-7149
DOI10.1109/TIP.2019.2903300
英文摘要Research in texture recognition often concentrates on recognizing textures with intraclass variations, such as illumination, rotation, viewpoint, and small-scale changes. In contrast, in real-world applications, a change in scale can have a dramatic impact on texture appearance to the point of changing completely from one texture category to another. As a result, texture variations due to changes in scale are among the hardest to handle. In this paper, we conduct the first study of classifying textures with extreme variations in scale. To address this issue, we first propose and then reduce scale proposals on the basis of dominant texture patterns. Motivated by the challenges posed by this problem, we propose a new GANet network where we use a genetic algorithm to change the filters in the hidden layers during network training in order to promote the learning of more informative semantic texture patterns. Finally, we adopt a Fisher vector pooling of a convolutional neural network filter bank feature encoder for global texture representation. Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding, we are developing a new dataset, the extreme scale variation textures (ESVaT), to test the performance of our framework. It is demonstrated that the proposed framework significantly outperforms the gold-standard texture features by more than 10% on ESVaT. We also test the performance of our proposed approach on the KTHTIPS2b and OS datasets and a further dataset synthetically derived from Forrest, showing the superior performance compared with the state-of-the-art.
资助项目Center for Machine Vision and Signal Analysis at the University of Oulu ; Tekes Fidipro Program[1849/31/2015] ; Business Finland Project[3116/31/2017] ; Infotech Oulu ; National Natural Science Foundation of China[61872379] ; Academy of Finland for Project MiGA[316765] ; ICT 2023 Project[313600] ; Project ICONICAL[313467] ; 6Genesis Flagship[318927]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000472609200004
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/4171]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Liu, Li
作者单位1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Waterloo, Dept Syst Design Engn, Waterloo, ON N2L 3G1, Canada
3.Peng Chong Lab, Shenzhen 518055, Peoples R China
4.Univ Oulu, Ctr Machine Vis & Signal Anal, Oulu 90014, Finland
5.Natl Univ Def Technol, Coll Syst Engn, Changsha 410073, Hunan, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Xilin,Liu, Li,Chen, Jie,et al. Texture Classification in Extreme Scale Variations Using GANet[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(8):3910-3922.
APA Chen, Xilin,Liu, Li,Chen, Jie,Zhao, Guoying,Fieguth, Paul,&Pietikainen, Matti.(2019).Texture Classification in Extreme Scale Variations Using GANet.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(8),3910-3922.
MLA Chen, Xilin,et al."Texture Classification in Extreme Scale Variations Using GANet".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.8(2019):3910-3922.

入库方式： OAI收割

来源：计算技术研究所

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。