搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于忆阻器的spiking神经网络在图像边缘提取中的应用

刘玉东 王连明

引用本文:
Citation:

基于忆阻器的spiking神经网络在图像边缘提取中的应用

刘玉东, 王连明

Application of memristor-based spiking neural network in image edge extraction

Liu Yu-Dong, Wang Lian-Ming
PDF
导出引用
  • 根据生物视觉系统的功能原理,用忆阻器模拟生物突触,结合忆阻器的记忆特性和spiking 神经网络的高效处理能力,构造了一种可用于图像边缘提取的三层spiking神经网络模型,该网络用忆阻器电导的变化量来表征图像边缘信息. 仿真结果表明,该方法的边缘提取结果具有连续性、光滑性、低误检漏检性和边缘定位准确性. 该神经网络的处理过程符合生物信息处理机制,为视觉系统的仿生实现提供了新的思路.
    By simulating biological synapses with memristors according to the function and principle of biological visual system and by combining the memory characteristic of memristor with high-efficient processing ability in spiking neural network, a three-layer spiking neural network model for image edge extraction is constructed, in which the image edge information is represented by the variation of the memristor conductance. The edge extraction result obtained with this approach has the characteristics of continuity, smoothness, low false leak detection and edge positioning accuracy. Since the processing mechanism of this neural network conforms to the biological counterpart, it offers a new idea for the bionic implementation of biological visual system.
    • 基金项目: 国家自然科学基金(批准号:21227008)和吉林省科技发展计划(批准号:20130102028JC)资助的课题.
    • Funds: Project supported by the National Natural Science Foundation of China (Grant No. 21227008) and the Jilin Provincial Development Program of Science and Technology, China (Grant No. 20130102028JC).
    [1]

    Li C, Shi D, Zou Y P 2012 Acta Phys. Sin. 61 070701 (in Chinese) [李承, 石丹, 邹云屏 2012 物理学报 61 070701]

    [2]

    Jin Q T, Wang J, Wei X L 2011 Acta Phys. Sin. 60 098701 (in Chinese) [金淇涛, 王江, 魏熙乐 2011 物理学报 60 098701]

    [3]

    Serrano-Gotarredona T, Masquelier T, Prodromakis T, Indiveri G, Linares-Barranco B 2013 Front. Neurosci. 7 2

    [4]

    Hu F W, Bao B C, Wu H G 2013 Acta Phys. Sin. 62 218401 (in Chinese) [胡丰伟, 包伯成, 武花干 2013 物理学报 62 218401]

    [5]

    Hong Q H, Zeng Y C, Li Z J 2013 Acta Phys. Sin. 62 230502 (in Chinese) [洪庆辉, 曾以成, 李志军 2013 物理学报 62 230502]

    [6]

    Afifi A, Ayatollahi A, Raissi F 2009 Proceedings of the European Conference on Circuit Theory and Design Conference Program Antalya, Turkey, August, 23-27, 2009 p563

    [7]

    Pershin Y V, Ventra D M 2010 Neural Networks 23 881

    [8]

    Ghosh D S, Adeli H 2009 Int. J. Neural Syst. 19 295

    [9]

    Egmont P M, De-ridder D, Handels H 2012 Patt. Recogn. 35 2279

    [10]

    Kim J J, Diamond D M 2002 Nat. Rev. Neurosci. 3 453

    [11]

    Strukov D B, Snider G S, Stewart D R, et al. 2008 Nature 453 80

    [12]

    Wang L M, Huang Y, Deng Y F 2008 J. Northeast Normal Univ. (Nat. Sci.) 40 346 (in Chinese) [王连明, 黄莹, 邓玉芬 2008 东北师大学报 (自然科学版) 40 346]

    [13]

    Song D H L M F, Ren X 2012 Acta Phys. Sin. 61 118101 (in Chinese) [宋德华, 吕梦菲, 任翔 2012 物理学报 61 118101]

    [14]

    Wang L D, Duan S K 2012 IJBC 22 1250205

    [15]

    Liang Y, Yu D S, Chen H 2013 Acta Phys. Sin. 62 158501 (in Chinese) [梁燕, 于东升, 陈昊 2013 物理学报 62 158501]

    [16]

    Fang X D, Tang Y H, Wu J J 2012 Chin. Phys. B 21 098901

    [17]

    Zhou J, Huang D 2012 Chin. Phys. B 21 048401

    [18]

    Jessell T M, Kande E R, Schwartz J H 2002 Principles of Neural Science (New York: McGraw-Hill) pp533-540

  • [1]

    Li C, Shi D, Zou Y P 2012 Acta Phys. Sin. 61 070701 (in Chinese) [李承, 石丹, 邹云屏 2012 物理学报 61 070701]

    [2]

    Jin Q T, Wang J, Wei X L 2011 Acta Phys. Sin. 60 098701 (in Chinese) [金淇涛, 王江, 魏熙乐 2011 物理学报 60 098701]

    [3]

    Serrano-Gotarredona T, Masquelier T, Prodromakis T, Indiveri G, Linares-Barranco B 2013 Front. Neurosci. 7 2

    [4]

    Hu F W, Bao B C, Wu H G 2013 Acta Phys. Sin. 62 218401 (in Chinese) [胡丰伟, 包伯成, 武花干 2013 物理学报 62 218401]

    [5]

    Hong Q H, Zeng Y C, Li Z J 2013 Acta Phys. Sin. 62 230502 (in Chinese) [洪庆辉, 曾以成, 李志军 2013 物理学报 62 230502]

    [6]

    Afifi A, Ayatollahi A, Raissi F 2009 Proceedings of the European Conference on Circuit Theory and Design Conference Program Antalya, Turkey, August, 23-27, 2009 p563

    [7]

    Pershin Y V, Ventra D M 2010 Neural Networks 23 881

    [8]

    Ghosh D S, Adeli H 2009 Int. J. Neural Syst. 19 295

    [9]

    Egmont P M, De-ridder D, Handels H 2012 Patt. Recogn. 35 2279

    [10]

    Kim J J, Diamond D M 2002 Nat. Rev. Neurosci. 3 453

    [11]

    Strukov D B, Snider G S, Stewart D R, et al. 2008 Nature 453 80

    [12]

    Wang L M, Huang Y, Deng Y F 2008 J. Northeast Normal Univ. (Nat. Sci.) 40 346 (in Chinese) [王连明, 黄莹, 邓玉芬 2008 东北师大学报 (自然科学版) 40 346]

    [13]

    Song D H L M F, Ren X 2012 Acta Phys. Sin. 61 118101 (in Chinese) [宋德华, 吕梦菲, 任翔 2012 物理学报 61 118101]

    [14]

    Wang L D, Duan S K 2012 IJBC 22 1250205

    [15]

    Liang Y, Yu D S, Chen H 2013 Acta Phys. Sin. 62 158501 (in Chinese) [梁燕, 于东升, 陈昊 2013 物理学报 62 158501]

    [16]

    Fang X D, Tang Y H, Wu J J 2012 Chin. Phys. B 21 098901

    [17]

    Zhou J, Huang D 2012 Chin. Phys. B 21 048401

    [18]

    Jessell T M, Kande E R, Schwartz J H 2002 Principles of Neural Science (New York: McGraw-Hill) pp533-540

计量
  • 文章访问数:  2635
  • PDF下载量:  1239
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-12-05
  • 修回日期:  2014-01-16
  • 刊出日期:  2014-04-05

基于忆阻器的spiking神经网络在图像边缘提取中的应用

  • 1. 东北师范大学物理学院, 长春 130024
    基金项目: 

    国家自然科学基金(批准号:21227008)和吉林省科技发展计划(批准号:20130102028JC)资助的课题.

摘要: 根据生物视觉系统的功能原理,用忆阻器模拟生物突触,结合忆阻器的记忆特性和spiking 神经网络的高效处理能力,构造了一种可用于图像边缘提取的三层spiking神经网络模型,该网络用忆阻器电导的变化量来表征图像边缘信息. 仿真结果表明,该方法的边缘提取结果具有连续性、光滑性、低误检漏检性和边缘定位准确性. 该神经网络的处理过程符合生物信息处理机制,为视觉系统的仿生实现提供了新的思路.

English Abstract

参考文献 (18)

目录

    /

    返回文章
    返回