OpenCL Implementations of a Genetic Algorithm for Feature Selection in Periocular Biometric Recognition

被引:0
|
作者
Fazendeiro, Paulo [1 ]
Padole, Chandrashekhar [1 ]
Sequeira, Pedro [1 ]
Prata, Paula [1 ]
机构
[1] Univ Beira Interior, Dept Informat, Inst Telecomunicacoes IT Portugal, Covilha, Portugal
关键词
GPGPU; Parallel Genetic Algorithms; Biometric Recognition; Periocular Recognition; OpenCL; Data Parallelism;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper explores OpenCL implementations of a genetic algorithm used to optimize the features vector in periocular biometric recognition. Using a multi core platform the algorithm is tested for CPU and GPU, exploring different parallelization levels for each operator of the genetic algorithm. The results show that using the GPU platform it is possible to accelerate the algorithm by several orders of magnitude, with a recognition rate similar to the one obtained in the sequential version. The results also show that it is possible to use only a small portion of the features without any degradation of the classifier's recognition rate.
引用
收藏
页码:729 / 737
页数:9
相关论文
共 50 条
  • [1] Feature Selection for Heart Rate Variability Based Biometric Recognition Using Genetic Algorithm
    Akhter, Nazneen
    Dabhade, Siddharth
    Bansod, Nagsen
    Kale, Karbhari
    [J]. INTELLIGENT SYSTEMS TECHNOLOGIES AND APPLICATIONS, VOL 1, 2016, 384 : 91 - 101
  • [2] Genetic & Evolutionary Type II Feature Extraction for Periocular-Based Biometric Recognition
    Simpson, Lamar
    Dozier, Gerry
    Adams, Joshua
    Woodard, Damon L.
    Miller, Philip
    Bryant, Kelvin
    Glenn, George
    [J]. 2010 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2010,
  • [3] Feature Selection for Biometric Iris Recognition
    Ivanko, K.
    Budik, N.
    Ivanushkina, N.
    [J]. 2017 5TH IEEE WORKSHOP ON ADVANCES IN INFORMATION, ELECTRONIC AND ELECTRICAL ENGINEERING (AIEEE'2017), 2017,
  • [4] (GEFE)under-bar: Genetic & Evolutionary Feature Extraction for Periocular-Based Biometric Recognition
    Adams, Joshua
    Woodard, Damon
    Dozier, Gerry
    Miller, Philip
    Glenn, George
    Bryant, Kelvin
    [J]. PROCEEDINGS OF THE 48TH ANNUAL SOUTHEAST REGIONAL CONFERENCE (ACM SE 10), 2010, : 235 - 238
  • [5] GENETIC ALGORITHM BASED FEATURE SELECTION FOR PARAPHRASE RECOGNITION
    Chitra, A.
    Rajkumar, Anupriya
    [J]. INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2013, 22 (02)
  • [6] A Comparison of Genetic Feature Selection and Weighting Techniques for Multi-Biometric Recognition
    Popplewell, Khary
    Alford, Aniesha
    Dozier, Gerry
    Bryant, Kelvin
    Kelly, John
    Adams, Josh
    Abegaz, Tamirat
    Purrington, Kamiliah
    Shelton, Joseph
    [J]. PROCEEDINGS OF THE 49TH ANNUAL ASSOCIATION FOR COMPUTING MACHINERY SOUTHEAST CONFERENCE (ACMSE '11), 2011, : 205 - 208
  • [7] Biometric recognition using feature selection and combination
    Kumar, A
    Zhang, D
    [J]. AUDIO AND VIDEO BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS, 2005, 3546 : 813 - 822
  • [8] Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition
    Schulte, Robert, V
    Prinsen, Erik C.
    Hermens, Hermie J.
    Buurke, Jaap H.
    [J]. FRONTIERS IN ROBOTICS AND AI, 2021, 8
  • [9] Periocular Biometric Recognition for Masked Faces
    HUANG Qiaoyue
    TANG Chaoying
    ZHANG Tianshu
    [J]. Wuhan University Journal of Natural Sciences, 2023, 28 (02) : 141 - 149
  • [10] A genetic algorithm based feature selection for handwritten digit recognition
    Ahlawat S.
    Rishi R.
    [J]. Recent Patents on Computer Science, 2019, 12 (04) : 304 - 316