The Problem of Sparse Image Coding

被引：0
作者：
Arthur E.C. Pece
机构：
[1] University of Copenhagen,Institute of Computer Science
来源：
Journal of Mathematical Imaging and Vision | 2002年 / 17卷
关键词：
sparse coding; atomic decomposition; adaptive representation; wavelet; matching pursuit; ICA;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Linear expansions of images find many applications in image processing and computer vision. Overcomplete expansions are often desirable, as they are better models of the image-generation process. Such expansions lead to the use of sparse codes. However, minimizing the number of non-zero coefficients of linear expansions is an unsolved problem. In this article, a generative-model framework is used to analyze the requirements, the difficulty, and current approaches to sparse image coding.
引用
收藏
页码：89 / 108
页数：19
相关论文
共 101 条
[1]  
Attias H.(1999)Independent factor analysis Neural Comp. 11 803-851
[2]  
Attneave F.(1954)Informational aspects of visual perception Psychol. Review 61 183-193
[3]  
Barlow H.B.(1972)Single units and sensation: A neuron doctrine for perceptual psychology Perception 1 371-394
[4]  
Barlow H.B.(1989)Unsupervised learning Neural Comp. 1 295-311
[5]  
Baum E.B.(1988)Internal representations for associative memory Biol. Cybern. 59 217-228
[6]  
Moody J.(1995)An information-maximization approach to blind separation and blind deconvolution Neural Computation 7 1129-1159
[7]  
Wilczeck F.(1997)The ‘independent components’ of natural scenes are edge filters Vision Res. 37 3327-3338
[8]  
Bell A.J.(2002)Dynamics of spatial frequency tuning in macaque VI J. Neurosci. 22 1976-1984
[9]  
Sejnowski T.J.(1993)Dynamics of orientation coding in area V1 of the awake monkey Visual Neurosci. 10 811-825
[10]  
Bell A.J.(1989)Orthogonal least squares methods and their application to non-linear system identification Int. J. Control 50 1873-1896
12345678910