Rotation-invariant recognition of copepods by circular harmonic filters.

被引:0
|
作者
Zavala-Hamz, VA [1 ]
Alvarez-Borrego, J [1 ]
机构
[1] Ctr Invest Cient & Educ Super Ensenada, Div Fis Aplicada, Dept Opt, Ensenada, Baja California, Mexico
关键词
D O I
10.1117/12.354764
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
The traditional identification of copepods is exhausting and time consuming. Perhaps that is the reason why in recent years the number of competent taxonomists has decreased significantly. Researchers have tried to automatize the identification process of marine microorganisms, but they have problems with the quality of the images and the orientation of the organisms. Rotation-invariant circular harmonic filters are generated in a computer, the computation time can be improved and the computer can work indefinitely. Three types of circular harmonic filters were studied in older to recognise and count copepods despite their orientation: Classical, phase only and multiple. Classical circular harmonic filters discriminated genus, species and sometimes sex, depending on the complexity of the organism. Phase only circular harmonic filters always differentiated among sexes. Multiple circular harmonic filters discarded false detections. The three types of circular harmonic filters recognised the target organism among others in a test image, so inexperienced observers can use them.
引用
收藏
页码:314 / 315
页数:2
相关论文
共 50 条
  • [41] Rotation-invariant pattern recognition using a joint transform correlator
    Chang, SD
    Boothroyd, S
    Palacharla, P
    Pachanathan, S
    [J]. OPTICS COMMUNICATIONS, 1996, 127 (1-3) : 107 - 116
  • [42] ROTATION-INVARIANT PATTERN-RECOGNITION USING A VECTOR REFERENCE
    WU, R
    STARK, H
    [J]. APPLIED OPTICS, 1984, 23 (06): : 838 - 840
  • [43] Multichannel photorefractive correlator for rotation-invariant optical pattern recognition
    Univ of New Orleans, New Orleans, United States
    [J]. Opt Commun, 4-6 (212-216):
  • [44] AN AUTOMATIC ROTATION-INVARIANT RECOGNITION TECHNIQUE FOR COLOR OBJECTS AND PATTERNS
    MITAL, DP
    GOH, WL
    [J]. JOURNAL OF MICROCOMPUTER APPLICATIONS, 1993, 16 (01): : 61 - 69
  • [45] Modified wavelet based morphological correlation for rotation-invariant recognition
    Wang, Qu
    Chen, Li
    Zhou, Jinyun
    Lin, Qinghua
    [J]. OPTICS AND LASER TECHNOLOGY, 2011, 43 (08): : 1504 - 1512
  • [46] Rotation-invariant target detection using a hybrid optical circular harmonic joint transform correlator with DC bias
    Huang, Xiaojing
    Huang, Xianlie
    [J]. Chinese Journal of Lasers B (English Edition), 1999, B8 (01): : 49 - 54
  • [47] IMPROVED ROTATION-INVARIANT DEGRADED PARTIAL PALMPRINT RECOGNITION TECHNIQUE
    Singh, Sanchit
    Correia, Paulo Lobato
    Soares, Luis Ducla
    [J]. 2013 INTERNATIONAL WORKSHOP ON BIOMETRICS AND FORENSICS (IWBF), 2013,
  • [48] Recognition of hand-written patterns by rotation-invariant neocognitron
    Satoh, S
    Kuroiwa, J
    Aso, H
    Miyake, S
    [J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 295 - 299
  • [49] Rotation-invariant Target Detection Using a Hybrid Optical Circular Harmonic Joint Transform Correlator with DC Bias
    HUANG Xiaojing (Department of Basic Science
    [J]. Chinese Journal of Lasers, 1999, (01) : 50 - 55
  • [50] Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters
    Giuffrida, Mario Valerio
    Tsaftaris, Sotirios A.
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 : 480 - 488