Acta Optica Sinica, Volume. 39, Issue 7, 0715005(2019)

Pose Invariant Face Recognition Using Maximum Gabor Similarity Based on Lucas-Kanade Algorithm

Chao Cheng1,2, Feipeng Da1,2, Chenxing Wang1,2、*, and Changjin Jiang1,2
Author Affiliations
  • 1 School of Automation, Southeast University, Nanjing, Jiangsu 210096, China
  • 2 Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, Jiangsu 210096, China
  • show less
    Figures & Tables(4)
    Diagrams of side face and full-frontal face patches
    Performance of Gabor similarity based on optimal parameter. (a) 1st patch; (b) 7th patch; (c) 9th patch; (d) 15th patch
    Synthesizing frontal face comparison based on Gabor optimal parameters and pixel difference optimal parameters
    • Table 1. Comparison of recognition rates of different approaches on FERET database

      View table

      Table 1. Comparison of recognition rates of different approaches on FERET database

      MethodRecognition rate /%
      -45°-30°30°45°
      LLR[4]55.089.577.053.0
      StackFlow[5]70.089.082.062.0
      MRF[6]91.097.396.591.5
      MVRL[7]96.299.2100.096.9
      CPF[8]98.4100.099.297.7
      MSMT[9]99.6100.0100.099.2
      Our approach96.998.499.297.7
    Tools

    Get Citation

    Copy Citation Text

    Chao Cheng, Feipeng Da, Chenxing Wang, Changjin Jiang. Pose Invariant Face Recognition Using Maximum Gabor Similarity Based on Lucas-Kanade Algorithm[J]. Acta Optica Sinica, 2019, 39(7): 0715005

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Dec. 12, 2018

    Accepted: Apr. 1, 2019

    Published Online: Jul. 16, 2019

    The Author Email: Wang Chenxing (cxwang@seu.edu.cn)

    DOI:10.3788/AOS201939.0715005

    Topics