• Laser & Optoelectronics Progress
  • Vol. 60, Issue 12, 1210015 (2023)
Zhou Zhang1,2, Xu Sun2,*, Rong Liu1, and Lianru Gao2
Author Affiliations
  • 1Faculty of Geomatics, East China University of Technology, Nanchang 330013, Jiangxi, China
  • 2Key Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
  • show less
    DOI: 10.3788/LOP221136 Cite this Article Set citation alerts
    Zhou Zhang, Xu Sun, Rong Liu, Lianru Gao. Band Selection of Hyperspectral Images Based on Fuzzy C-Means Clustering and Firefly Algorithm[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1210015 Copy Citation Text show less
    FCM-FA band selection process
    Fig. 1. FCM-FA band selection process
    Classification accuracy of different methods on Indian Pines dataset. (a) OA of the SVM classifier; (b) OA of the KNN classifier; (c) Kappa coefficient of the SVM classifier; (d) Kappa coefficient of the KNN classifier
    Fig. 2. Classification accuracy of different methods on Indian Pines dataset. (a) OA of the SVM classifier; (b) OA of the KNN classifier; (c) Kappa coefficient of the SVM classifier; (d) Kappa coefficient of the KNN classifier
    Classification accuracy of different methods on PaviaU dataset. (a) OA of SVM classifier; (b) OA of KNN classifier; (c) Kappa coefficient of SVM classifier; (d) Kappa coefficient of KNN classifier
    Fig. 3. Classification accuracy of different methods on PaviaU dataset. (a) OA of SVM classifier; (b) OA of KNN classifier; (c) Kappa coefficient of SVM classifier; (d) Kappa coefficient of KNN classifier
    Classification accuracy of different methods in 28 selected bands on Indian Pines dataset using different proportions of training samples. (a) OA of SVM classifier; (b) OA of KNN classifier; (c) Kappa coefficient of SVM classifier; (d) Kappa coefficient of KNN classifier
    Fig. 4. Classification accuracy of different methods in 28 selected bands on Indian Pines dataset using different proportions of training samples. (a) OA of SVM classifier; (b) OA of KNN classifier; (c) Kappa coefficient of SVM classifier; (d) Kappa coefficient of KNN classifier
    Classification accuracy of different methods in 18 selected bands on PaviaU dataset using different proportions of training samples. (a) OA of SVM classifier; (b) OA of KNN classifier; (c) Kappa coefficient of SVM classifier; (d) Kappa coefficient of KNN classifier
    Fig. 5. Classification accuracy of different methods in 18 selected bands on PaviaU dataset using different proportions of training samples. (a) OA of SVM classifier; (b) OA of KNN classifier; (c) Kappa coefficient of SVM classifier; (d) Kappa coefficient of KNN classifier
    Spectral characteristic curves of land type on Indian Pines dataset. (a)-(p) Characteristic curves of land type 1-16, respectively
    Fig. 6. Spectral characteristic curves of land type on Indian Pines dataset. (a)-(p) Characteristic curves of land type 1-16, respectively
    Spectral characteristic curves of land type on PaviaU dataset. (a)~(i) Characteristic curves of land type 1-9, respectively
    Fig. 7. Spectral characteristic curves of land type on PaviaU dataset. (a)~(i) Characteristic curves of land type 1-9, respectively
    DatasetISSCEGCSR-REGCSR-COPBSSpaBSFCMFCM-FA
    Indian Pines9.470.128.374.23127.1342.01163.69
    PaviaU40.630.542.1911.22542.49258.19553.92
    Table 1. Calculation time of different methods
    DatasetN=5N=8N=10N=12N=15
    Indian Pines155.19160.91163.69170.61176.33
    PaviaU523.84539.57553.92563.52572.99
    Table 2. Calculation time of FCM-FA for different fireflies
    DatasetClassifierParameterN=5N=8N=10N=12N=15
    Indian PinesSVMOA80.36883.34083.72283.56885.134
    AA80.21683.33483.71483.53685.035
    Kappa77.51480.92981.36681.19383.008
    KNNOA66.55772.43472.65572.68674.999
    AA66.07972.23772.52172.60374.886
    Kappa61.70868.49168.74368.79071.400
    PaviaUSVMOA94.21494.21494.21494.21494.214
    AA94.19994.19994.19994.19994.199
    Kappa92.31592.31592.31592.31592.315
    KNNOA89.37989.37989.37989.37989.379
    AA89.39389.39389.39389.39389.393
    Kappa85.72085.72085.72085.72085.720
    Table 3. Effect of the setting of number of fireflies on results of FCM-FA band selection (band quality is indirectly evaluated through classification accuracy)
    Zhou Zhang, Xu Sun, Rong Liu, Lianru Gao. Band Selection of Hyperspectral Images Based on Fuzzy C-Means Clustering and Firefly Algorithm[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1210015
    Download Citation