Band selection for heterogeneity classification of hyperspectral transmission images based on multi-criteria ranking

被引:9
|
作者
Li, Gang [1 ,2 ]
Ma, Shuangshuang [1 ,2 ]
Li, Ke [3 ]
Zhou, Mei [4 ]
Lin, Ling [1 ,2 ]
机构
[1] Tianjin Univ, State Key Lab Precis Measuring Technol & Instrumen, Tianjin 300072, Peoples R China
[2] Tianjin Univ, Tianjin Key Lab Biomed Detecting Tech & Instrument, Tianjin 300072, Peoples R China
[3] Tianjin Univ Hosp, Dept Obstet & Gynecol, Tianjin 300072, Peoples R China
[4] East China Normal Univ, Shanghai Key Lab Multidimens Informat Proc, Shanghai 200241, Peoples R China
关键词
Band selection; Multi -criteria ranking method; Heterogeneity classification; Hyperspectral transmission images; FEATURE-EXTRACTION; RESTORATION;
D O I
10.1016/j.infrared.2022.104317
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
Hyperspectral images contain hundreds of continuous spectral bands, which can provide rich information for target detection and image classification. However, high-dimensional data are easy to cause the "Hughes phenomenon", which affects the classification accuracy of images. In this paper, a band selection method based on multi-criteria ranking is proposed for hyperspectral dimensionality reduction. First, the hyperspectral image acquisition system is built to collect the hyperspectral transmission image datasets containing various heterogeneities. Second, the original data are preprocessed and the band selection method proposed is used for data dimensionality reduction. That is, (1) the whole band is divided into subintervals according to the correlation criteria, and then the bands with large information amount and good inter-class separability are selected according to other criteria functions, (2) the bands of each subinterval are combined, and the combined bands are evaluated according to the optimum index factor and Bhattacharyya distance, and (3) the combined bands are ranked and the top-ranked combined bands are selected as the representative bands for image classification. Finally, the support vector machine is used to verify the effectiveness of the representative bands selected by this method. The experimental results show that the proposed method achieves data dimensionality reduction, and the overall classification accuracy can reach 100% on some selected subsets of bands, which has better classification performance than other related band selection methods. In addition, the computational complexity of high-dimensional data can be effectively reduced by band selection, and the average running time is 95.19% less than that of the full bands while ensuring classification accuracy.
引用
收藏
页数:9
相关论文
共 50 条
  • [21] Probabilistic histogram-based band selection and its effect on classification of hyperspectral images
    Patro, Ram Narayan
    Subudhi, Subhashree
    Biswal, Pradyut Kumar
    Sahoo, Harish Kumar
    Advances in Intelligent Systems and Computing, 2019, 816 : 559 - 570
  • [22] Real-time Multi-Criteria Classification of Facial Images
    Marinov, Radoslav
    Chen, Zhifeng
    Reznik, Yuriy
    APPLICATIONS OF DIGITAL IMAGE PROCESSING XLII, 2019, 11137
  • [23] Multi-Criteria Based Federation Selection in Cloud
    Ray, Benay Kumar
    Middya, Asif Iqbal
    Roy, Sarbani
    Khatua, Sunirmal
    2017 9TH INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS AND NETWORKS (COMSNETS), 2017, : 182 - 189
  • [24] A DEA-BASED APPROACH TO RANKING MULTI-CRITERIA ALTERNATIVES
    Koeksalan, Murat
    Tuncer, Ceren
    INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING, 2009, 8 (01) : 29 - 54
  • [25] OMCR: An Opinion-Based Multi-Criteria Ranking Approach
    Abulaish, Muhammad
    Jahiruddin
    Bhardwaj, Anjali
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2019, 36 (01) : 397 - 411
  • [26] Genetic Algorithm Based Feature Ranking in Multi-criteria Optimization
    Suguna, N.
    Thanushkodi, K.
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2009, 9 (06): : 132 - 141
  • [27] RANKING THE IMPORTANCE OF MULTI-CRITERIA EVALUATION INDICATORS BASED ON THEIR TRANSITIVITY
    Ginevicius, Romualdas
    Nazarko, Joanicjusz
    Gedvilaite, Dainora
    Petraskevicius, Vladislavas
    ECONOMICS & SOCIOLOGY, 2023, 16 (04) : 309 - 320
  • [28] SPARSE REPRESENTATION BASED BAND SELECTION FOR HYPERSPECTRAL IMAGES
    Li, Shuangjiang
    Qi, Hairong
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011,
  • [29] Band Selection for Hyperspectral Images Based on Impurity Function
    Chang, Yang-Lang
    Shu, Bin-Feng
    Hsieh, Tung-Ju
    Chu, Chih-Yuan
    Fang, Jyh-Perng
    2011 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2011, : 2369 - 2372
  • [30] PROBLEM-BASED BAND SELECTION FOR HYPERSPECTRAL IMAGES
    Habermann, Mateus
    Fremont, Vincent
    Shiguemori, Elcio Hideiti
    2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2017, : 1800 - 1803