Rotation-invariant pattern recognition: A procedure slightly inspired on olfactory system and based on Kohonen network

被引：0
|
作者：
Palermo, M. B.
Monteiro, L. H. A.
机构：
[1] Univ Presbiteriana Mackenzie, Posgrad Engn Elect, Escola Engn, BR-01302907 Sao Paulo, Brazil
[2] Univ Sao Paulo, Dept Engn Telecommun & Controle, Escola Politecn, BR-05508900 Sao Paulo, Brazil
来源：
ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 2 | 2006年 / 4132卷
关键词：
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：
A computational scheme for rotation-invariant pattern recognition based on Kohonen neural network is developed. This scheme is slightly inspired on the vertebrate olfactory system, and its goal is to recognize spatiotemporal patterns produced in a two-dimensional cellular automaton that would represent the olfactory bulb activity when submitted to odor stimuli. The recognition occurs through a multi-layer Kohonen network that would represent the olfactory cortex. The recognition is invariant to rotations of the patterns, even when a noise lower than 1% is added.
引用
收藏
页码：444 / 450
页数：7
相关论文
共 50 条
  • [21] Nonlinear rotation-invariant pattern recognition by use of the optical morphological correlation
    Garcia-Martinez, Pascuala
    Ferreira, Carlos
    Garcia, Javier
    Arsenault, Henri H.
    Applied Optics, 2000, 39 (05): : 776 - 781
  • [22] Nonlinear rotation-invariant pattern recognition by use of the optical morphological correlation
    Garcia-Martinez, P
    Ferreira, C
    Garcia, J
    Arsenault, HH
    APPLIED OPTICS, 2000, 39 (05) : 776 - 781
  • [23] PROPERTIES OF THE CIRCULAR HARMONIC EXPANSION FOR ROTATION-INVARIANT PATTERN-RECOGNITION
    ARSENAULT, HH
    SHENG, YL
    APPLIED OPTICS, 1986, 25 (18): : 3225 - 3229
  • [24] NEURAL NETWORKS - TRANSLATION-INVARIANT, ROTATION-INVARIANT, AND SCALE-INVARIANT PATTERN-RECOGNITION
    DOTSENKO, VS
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1988, 21 (15): : L783 - L787
  • [25] Modified wavelet based morphological correlation for rotation-invariant recognition
    Wang, Qu
    Chen, Li
    Zhou, Jinyun
    Lin, Qinghua
    OPTICS AND LASER TECHNOLOGY, 2011, 43 (08): : 1504 - 1512
  • [26] A Multi-Scale Convolutional Neural Network for Rotation-Invariant Recognition
    Hong, Tzung-Pei
    Hu, Ming-Jhe
    Yin, Tang-Kai
    Wang, Shyue-Liang
    ELECTRONICS, 2022, 11 (04)
  • [27] ROTATION-INVARIANT DIGITAL PATTERN-RECOGNITION USING CIRCULAR HARMONIC EXPANSION
    HSU, YN
    ARSENAULT, HH
    APRIL, G
    APPLIED OPTICS, 1982, 21 (22): : 4012 - 4015
  • [28] ROTATION-INVARIANT PATTERN-RECOGNITION USING OPTIMUM FEATURE-EXTRACTION
    WU, R
    STARK, H
    APPLIED OPTICS, 1985, 24 (02): : 179 - 184
  • [29] ROTATION-INVARIANT PATTERN-RECOGNITION AMONG ALMOST-SIMILAR OBJECTS
    ARSENAULT, HH
    HSU, YN
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA, 1982, 72 (12) : 1788 - 1788
  • [30] PATTERN RECOGNITION USING ROTATION-INVARIANT FILTER-DRIVEN TEMPLATE MATCHING
    Zeng, Yi-Chong
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011,
12345