CHARACTER-RECOGNITION USING A DYNAMIC OPTOELECTRONIC NEURAL NETWORK WITH UNIPOLAR BINARY WEIGHTS

被引：3
|
作者：
OITA, M
TAKAHASHI, M
TAI, S
KYUMA, K
机构：
[1] Central Research Laboratory, Mitsubishi Electric Corporation, Amagasaki, Hyogo, 661, 8-1-1, Tsukaguchi-Honmachi
来源：
OPTICS LETTERS | 1990年 / 15卷 / 21期
关键词：
D O I：
10.1364/OL.15.001227
中图分类号：
O43 [光学];
学科分类号：
070207 ; 0803 ;
摘要：
A novel type of quantized learning rule with unipolar binary weights that is useful for the optical implementation of neural networks is reported. An input-dependent thresholding operation is also proposed to remove the unwanted effects that are due to the insufficient contrast ratio of spatial light modulators as synaptic connection devices. Moreover, we experimentally demonstrate the recognition of 26 characters of the alphabet by using the single set of an optoelectronic three-layered network. © 1990 Optical Society of America.
引用
收藏
页码：1227 / 1229
页数：3
相关论文
共 50 条
  • [41] Binary decision clustering for neural-network-based optical character recognition
    Wilson, CL
    Grother, PJ
    Barnes, CS
    PATTERN RECOGNITION, 1996, 29 (03) : 425 - 437
  • [42] Recognition mechanism of a neural network for character recognition
    Shintani, H.
    Akutagawa, M.
    Nagashino, H.
    Kinouchi, Y.
    2005 27TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-7, 2005, : 6540 - 6543
  • [43] Character recognition using Matlab's neural network toolbox
    Prasad, K. (Kauleshwarprasad2@gmail.com), 1600, Science and Engineering Research Support Society, 20 Virginia Court, Sandy Bay, Tasmania, Prof B.H.Kang's Office,, Australia (06):
  • [44] BENGALI ALPHA-NUMERIC CHARACTER-RECOGNITION USING CURVATURE FEATURES
    DUTTA, A
    CHAUDHURY, S
    PATTERN RECOGNITION, 1993, 26 (12) : 1757 - 1770
  • [45] Recognition of Handwritten Devanagari Character using Convolutional Neural Network
    Dokare, Indu
    Gadge, Siddhesh
    Kharde, Kedar
    Bhere, Siddhesh
    Jadhav, Rohit
    ICSPC'21: 2021 3RD INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION (ICPSC), 2021, : 353 - 359
  • [46] Amharic Character Recognition Using Deep Convolutional Neural Network
    Aynalem, Achamie
    ARTIFICIAL INTELLIGENCE AND DIGITALIZATION FOR SUSTAINABLE DEVELOPMENT, ICAST 2022, 2023, 455 : 177 - 195
  • [47] Handwriting Arabic Character Recognition LeNet Using Neural Network
    Al-Jawfi, Rashad
    INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2009, 6 (03) : 304 - 309
  • [48] Persian Handwritten Character Recognition Using Convolutional Neural Network
    Sarvaramini, Farzin
    Nasrollahzadeh, Alireza
    Soryani, Mohsen
    26TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE 2018), 2018, : 1676 - 1680
  • [49] Artificial neural network based character recognition using SciLab
    Darshni, Priya
    Dhaliwal, Balwinder Singh
    Kumar, Raman
    Balogun, Vincent Aizebeoje
    Singh, Sunpreet
    Pruncu, Catalin Iulian
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (02) : 2517 - 2538
  • [50] Artificial neural network based character recognition using SciLab
    Priya Darshni
    Balwinder Singh Dhaliwal
    Raman Kumar
    Vincent Aizebeoje Balogun
    Sunpreet Singh
    Cătălin Iulian Pruncu
    Multimedia Tools and Applications, 2023, 82 : 2517 - 2538
12345