[1]尚 丽,杜吉祥,翟传敏.稀疏编码算法概述[J].苏州市职业大学学报,2009,(01):5-10.
 SHANG Li,DU Ji-xiang,ZHAI Chuan-min.Overview of Sparse Coding Algorithm[J].,2009,(01):5-10.
点击复制

稀疏编码算法概述
分享到:

《苏州市职业大学学报》[ISSN:1008-5475/CN:32-1524/G4]

卷:
期数:
2009年01期
页码:
5-10
栏目:
研究综述(快报)
出版日期:
2009-03-25

文章信息/Info

Title:
Overview of Sparse Coding Algorithm
文章编号:
文章编号:1008-5475(2009)01-00
作者:
尚 丽1杜吉祥234翟传敏2
(1. 苏州市职业大学 电子信息工程系,江苏 苏州 215104;2.华侨大学 计算机科学与技术学院,福建 泉州 362021; 3.中国科学技术大学 信息技术学院,安徽 合肥 230026;4.中国科学院合肥智能机械研究所,安徽 合肥 230031)
Author(s):
SHANG Li1 DU Ji-xiang234 ZHAI Chuan-min2
(1. Department of Electronic Information Engineering, Suzhou Vocational University, Suzhou 215104, China; 2. College of Computer Science and Technology, Huaqiao University, Quanzhou 362021, China; 3. College of Automation, University of Science and Technology of China, Hefei 230026, China; 4. Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, China)
关键词:
关键词:稀疏编码V1区感受野神经网络
Keywords:
Key words: sparse coding V1 field receptive fields neural network
分类号:
中图分类号:TN911 .73
文献标志码:
A
摘要:
摘 要:稀疏编码是一种模拟哺乳动物视觉系统主视皮层V1区简单细胞感受野的人工神经网络方法.该方法具有空间的局部性、方向性和频域的带通性,是一种自适应的图像统计方法.主要从稀疏编码的研究意义、数学描述、研究历史、研究现状和存在的问题、应用领域等方面对稀疏编码算法进行概述,最后指出该算法进一步的研究方向.
Abstract:
Abstract: The sparse coding algorithm is an artificial neural network method, which can model the receptive fields of simple cells in the mammalian primary visual cortex in brain, also known as V1. This method has the spatially localized, oriented, and bandpass, and is a self-adaptive signal statistical method. This paper mainly summarizes the SC algorithm form the following aspects, such as the research meaning, the mathematical description, the research history, the research situation actuality and current problems, the applications, and so on. Finally, the further research direction is also given.

参考文献/References:

参考文献: [1] 尚 丽. 稀疏编码算法及其应用研究[D]. 合肥:中国科学技术大学,2006. [2] HUBEL D H, WIESEL T N. Receptive fields of single neurons in the cat’s striate cortex[J]. Journal of Physiology, 1959, 148: 574-591. [3] HUBEL D H, WIESEL T N. Receptive fields, binocular interaction and functional architecture the cat’s visual cortex[J]. Journal of Physiology,1962, 160:106-154. [4] HUBEL D H, WIESEL T N. Receptive fields and functional architecture of monkey striate cortex[J]. Journal of Physiology, 1968, 195:215-243. [5] BARLOW H B. The coding of sensory messages[M]//THORPE W H, ZANGWILL O L. Current Problems in Animal Behaviors: Chapter XIII. London: Cambridge University Press, 1961: 331-360. [6] 尚 丽, 郑春厚. 基于稀疏编码的自然图像特征提取及去噪[J]. 系统仿真学报,2005, 17(7): 1782-1784. [7] ZETZSCHE C. Sparse coding: the link between low level vision and associative memory[M]//ECKMILLER R, HAARTMANN G, HAUSKE G. Parallel Processing in Neural Systems and Computes. Amsterdam:Springer- Verlag, 1990. [8] OLSHAUSEN B A, FIELD D J. Sparse coding with an overcomplete basis set: a strategy employed by V1[J]. Vision Research, 1997, 37:3311 -3325. [9] WILLSHAW D J, BUNEMAN O P, LONGUET HIGGINS H C. Nonholographic associative memory[J]. Nature, 1969, 222(5): 960-962. [10] BARLOW H B. Single units and sensation: A neuron doctrine for perceptual psychology[J]. Perception, 1972, 1: 371-394. [11 ] FIELD D J. Relations between the statistics of natural images and the response properties of cortical cells[J]. Journal Optical Society, 1987, 4:2379-2394. [12] MICHISON G. The organization of sequential memory: sparse representations and the targeting problem[M]// SEELEN W V, SHAW G, LEINBOS U M. Organiztion of Neural Networks, Weinheim: VCH Verlagsgesellschaft, 1988: 347-367. [13] ROLL E T, TREVES A. The relative advantages of sparse versus distributed encoding for associative neuronal networks in the brain[J]. Network, 1990, 1(4):407-421. [14] ROLL E T, TOVEE M J. Sparseness of the neuronal representation of stmuli in the primate temporal visual cortex[J]. Journal of Neurophysiology, 1995, 173:713-726. [15] YONG M P, YAMANE S Y. Sparse population coding of faces in the inferotemporal cortex[J]. Science,1992, 256:1327-1330. [16] FERSTER D, CHUNG S, WHEAT H. Orientation selectivity of thalamic input to simple cells of cat visual cortex[J]. Nature, 1996, 380:249-252. [17] FIELD D J. What the statistics of natural images tell us about visual coding[J]. Proceedings of the International Society for Optical Engineering (SPIE),1989, 1077: 269-276. [18] OLSHAUSEN B A, FIELD D J. Emergence of simple-cell receptive field properties by learning a sparse code for 2009年第1期 尚 丽等:稀疏编码算法概述苏州市职业大学学报 第20卷 - 10 - natural images[J]. Nature, 1996, 381: 607-609. [19] JOSHUA B. TENENBAUM, WILLIAM T F. Separating style and content with bilinear models [J]. Neural Computation, 2000, 12:1247-1283. [ 2 0 ] OL SHAUS EN B A, PHI L S , MICHAE L S L . L e a r n i n g s p a r s e ima g e c o d e s u s i n g a wa v e l e t p y r ami d architecture[J]. Advances in Neural Information Processing Systems, 2001, 13: 887-893. [21] HYVÄRINEN A, HOYER P O. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images[J]. Vision Research, 2001, 41(18): 2413-2423. [22] 杨 谦, 齐翔林, 汪云九. 视皮层V1区简单细胞的稀疏编码策略[J]. 计算物理, 2001, 18(2):136-143. [23] SHANG Li, HUANG Deshuang, ZHENGz Chunhou, et al. Image feature extraction based on an extended non-negative sparse coding neural network model[J]. Lecture Notes in Computer Science (LNCS), 2005, 3497: 807-812. [24] SHANG Li, HUANG Deshuang. Image denoising using non-negative sparse coding shrinkage algorithm[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’2005). USA: San Diego, CA, 2005, 1: 1017-1022. [25] 尚 丽, 陈 杰, 周 燕,等. 基于非负稀疏编码的图像特征提取及应用[J]. 苏州市职业大学学报, 2007, 18(2): 51-54. [26] HOYER P O. Modeling receptive fields with non-negative sparse coding[C]//SCHUTTER E D. Computational Neuroscience: Trends in Research 2003. Amsterdam: Elsevier, 2003. [27] SHANG Li, CAO Fengwen. Adaptive denoising using a modified sparse coding shrinkage method[J]. Neural Processing Letters, 2006, 24(2): 153-162. [28] SHANG Li, HUANG Deshuang, ZHENG Chunhou, et al. Noise removal using a novel non-negative sparse coding shrinkage technique[J]. Neurocomputing, 2006, 69 (7/9): 874-877. [29] 尚 丽, 陈 杰. 基于非负稀疏编码和RBPNN的掌纹图像识别方法[J]. 苏州市职业大学学报, 2008, 19(1): 65-69. [30] SHANG Li, HUANG Deshuang, DU Jixiang, et al. Palmprint recognition using FastICA algorithm and radial basis probabilistic neural network[J]. Neurocomputing, 2006, 69(13/15): 1782-1786. ( 责任编辑: 李 华)

备注/Memo

备注/Memo:
收稿日期:2008-11 -14;修回日期:2008-12-15
基金项目:江苏省青蓝工程资助项目;中国博士后科学基金项目(20060390180);国家自然科学基金(青年基金)项目(60805021);福建省自然科
学基金项目(A0810010,A0740001)
作者简介:尚 丽(1972-),女,安徽砀山人,副教授、高级工程师,博士,主要从事人工神经网络、数字信号处理、智能计算等研究;杜吉祥
(1977-),男,山东高唐人,讲师,博士,硕士生导师,主要从事图像处理、模式识别,机器学习研究.
更新日期/Last Update: 2009-04-07