• Infrared and Laser Engineering
  • Vol. 51, Issue 4, 20210309 (2022)
Mianrong Yang1 and Liping Niu2
Author Affiliations
  • 1Computer and Information Engineering College, Xinxiang University, Xinxiang 453003, China
  • 2College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, China
  • show less
    DOI: 10.3788/IRLA20210309 Cite this Article
    Mianrong Yang, Liping Niu. Zernike’s feature selection based on LGBM and identification methods of infrared image target[J]. Infrared and Laser Engineering, 2022, 51(4): 20210309 Copy Citation Text show less
    Flow chart of Zernike’s feature selection based on LGBM and identification methods of infrared image target
    Fig. 1. Flow chart of Zernike’s feature selection based on LGBM and identification methods of infrared image target
    Illustrations of the 10 targets in MWIR dataset
    Fig. 2. Illustrations of the 10 targets in MWIR dataset
    Performance of different methods under noise corruption
    Fig. 3. Performance of different methods under noise corruption
    Performance of different methods under partially missing
    Fig. 4. Performance of different methods under partially missing
    ClassPickupSUVBTR70BRDM2BMP2T72ZSU23/42S3MTLBD20Recognition rate
    Pickup9702010000097%
    SUV0980100000198%
    BTR70001000000000100%
    BRDM21109800000098%
    BMP20010970010197%
    T720002196010096%
    ZSU23/42010009700097%
    2S3000000010000100%
    MTLB0000000099199%
    D200101010009797%
    Average97.9%
    Table 1. Recognition results of the proposed method on the original test samples
    MethodAverage recognition rate
    Proposed method97.9%
    SVM94.5%
    SRC95.1%
    Zernike96.9%
    CNN97.2%
    Table 2. Performance of different methods on original samples
    Mianrong Yang, Liping Niu. Zernike’s feature selection based on LGBM and identification methods of infrared image target[J]. Infrared and Laser Engineering, 2022, 51(4): 20210309
    Download Citation