The problem of sparse image coding

被引:32
作者
Pece, AEC [1 ]
机构
[1] Univ Copenhagen, Inst Comp Sci, DK-2100 Copenhagen, Denmark
关键词
sparse coding; atomic decomposition; adaptive representation; wavelet; matching pursuit; ICA;
D O I
10.1023/A:1020677318841
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
Linear expansions of images find many applications in image processing and computer vision. Over-complete 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:20
相关论文
共 77 条
[1]
[Anonymous], 1995, The Handbook of Brain Theory and Neural Networks
[2]
[Anonymous], 1990, SUBSET SELECTION REG, DOI DOI 10.1007/978-1-4899-2939-6
[3]
Independent factor analysis [J].
Attias, H .
NEURAL COMPUTATION, 1999, 11 (04) :803-851
[4]
SOME INFORMATIONAL ASPECTS OF VISUAL PERCEPTION [J].
ATTNEAVE, F .
PSYCHOLOGICAL REVIEW, 1954, 61 (03) :183-193
[5]
Barlow H., 1961, SENS COMMUN, P217, DOI DOI 10.7551/MITPRESS/9780262518420.003.0013
[6]
Unsupervised Learning [J].
Barlow, H. B. .
NEURAL COMPUTATION, 1989, 1 (03) :295-311
[7]
Barlow H B, 1972, Perception, V1, P371, DOI 10.1068/p010371
[8]
Barlow H.B., 1994, LARGE SCALE NEURONAL, P1
[9]
INTERNAL REPRESENTATIONS FOR ASSOCIATIVE MEMORY [J].
BAUM, EB ;
MOODY, J ;
WILCZEK, F .
BIOLOGICAL CYBERNETICS, 1988, 59 (4-5) :217-228
[10]
AN INFORMATION MAXIMIZATION APPROACH TO BLIND SEPARATION AND BLIND DECONVOLUTION [J].
BELL, AJ ;
SEJNOWSKI, TJ .
NEURAL COMPUTATION, 1995, 7 (06) :1129-1159