Multi-class target recognition based on adaptive feature selection

被引:2
|
作者
Wang, Yuehuan [1 ,2 ]
Yao, Wei [1 ]
Song, Yunfeng [1 ]
Sang, Nong [2 ]
Zhang, Tianxu [2 ]
机构
[1] Huazhong Univ Sci & Technol, Inst Pattern Recognit & AI, Wuhan 430074, Peoples R China
[2] Natl Key Lab Sci & Tech, Multi Spectral Informat Proc Technol, Wuhan 430074, Peoples R China
关键词
remote sensing image; adaptive feature selection; multiclass target recognition;
D O I
10.1117/12.850649
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
In this paper, a new approach of multi-class target recognition is proposed for remote sensing image analysis. A multi-class feature model is built, which is based on sharing features among classes. In order to make the recognition process efficient, we adopted the idea of adaptive feature selection. In each layer of the integrated feature model, the most salient and stable feature are selected first, and then the less ones. Experiments demonstrated the approach proposed is efficient in computation and is adaptive to scene variation.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Structured multi-class feature selection with an application to face recognition
    Zini, Luca
    Noceti, Nicoletta
    Fusco, Giovanni
    Odone, Francesca
    [J]. PATTERN RECOGNITION LETTERS, 2015, 55 : 35 - 41
  • [2] Structured Multi-class Feature Selection for Effective Face Recognition
    Fusco, Giovanni
    Zini, Luca
    Noceti, Nicoletta
    Odone, Francesca
    [J]. IMAGE ANALYSIS AND PROCESSING (ICIAP 2013), PT 1, 2013, 8156 : 410 - 419
  • [3] Extended adaptive Lasso for multi-class and multi-label feature selection
    Chen, Si-Bao
    Zhang, Yu-Mei
    Ding, Chris H. Q.
    Zhang, Jian
    Luo, Bin
    [J]. KNOWLEDGE-BASED SYSTEMS, 2019, 173 : 28 - 36
  • [4] Multi-Class SVM Based Gradient Feature for Banknote Recognition
    Dittimi, Tamarafinide V.
    Hmood, Ali K.
    Suen, Ching Y.
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2017, : 1030 - 1035
  • [5] Feature selection with multi-class logistic regression
    Wang, Jingyu
    Wang, Hongmei
    Nie, Feiping
    Li, Xuelong
    [J]. NEUROCOMPUTING, 2023, 543
  • [6] Scalable Feature Selection for Multi-class Problems
    Chidlovskii, Boris
    Lecerf, Loic
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, PART I, PROCEEDINGS, 2008, 5211 : 227 - 240
  • [7] Multi-class feature selection for texture classification
    Chen, Xue-wen
    Zeng, Xiangyan
    van Alphen, Deborah
    [J]. PATTERN RECOGNITION LETTERS, 2006, 27 (14) : 1685 - 1691
  • [8] Feature subset selection for multi-class SVM based image classification
    Wang, Lei
    [J]. COMPUTER VISION - ACCV 2007, PT II, PROCEEDINGS, 2007, 4844 : 145 - 154
  • [9] Multi-class feature selection by exploring reliable class correlation
    Wang, Zhenyu
    Wang, Chenchen
    Wei, Jinmao
    Liu, Jian
    [J]. KNOWLEDGE-BASED SYSTEMS, 2021, 230
  • [10] Feature selection based on fuzzy extension matrix for multi-class problem
    Wang, XZ
    Lu, XY
    Zhang, F
    [J]. PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 2032 - 2035