Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model

被引:144
作者
Lee, AB [1 ]
Mumford, D
Huang, J
机构
[1] Brown Univ, Dept Phys, Providence, RI 02912 USA
[2] Brown Univ, Div Appl Math, Providence, RI 02912 USA
基金
美国国家科学基金会;
关键词
natural images; stochastic image model; non-Gaussian statistics; scaling; dead leaves model; occlusions; clutter;
D O I
10.1023/A:1011109015675
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We develop a scale-invariant version of Matheron's "dead leaves model" for the statistics of natural images. The model takes occlusions into account and resembles the image formation process by randomly adding independent elementary shapes, such as disks, in layers. We compare the empirical statistics of two large databases of natural images with the statistics of the occlusion model, and find an excellent qualitative, and good quantitative agreement. At this point, this is the only image model which comes close to duplicating the simplest, elementary statistics of natural images-such as, the scale invariance property of marginal distributions of filter responses, the full co-occurrence statistics of two pixels, and the joint statistics of pairs of Haar wavelet responses.
引用
收藏
页码:35 / 59
页数:25
相关论文
共 34 条
[1]   The size of objects in natural and artificial images [J].
Alvarez, L ;
Gousseau, Y ;
Morel, JM .
ADVANCES IN IMAGING AND ELECTRON PHYSICS, VOL 111, 1999, 111 :167-242
[2]   Image compression via joint statistical characterization in the wavelet domain [J].
Buccigrossi, RW ;
Simoncelli, EP .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1999, 8 (12) :1688-1701
[3]   RELATIONS BETWEEN THE STATISTICS OF NATURAL IMAGES AND THE RESPONSE PROPERTIES OF CORTICAL-CELLS [J].
FIELD, DJ .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1987, 4 (12) :2379-2394
[4]  
FREEMAN WT, 1999, P IEEE INT C COMP VI
[5]  
GRENANDER U, 2000, IN PRESS IEEE T PAMI
[6]  
Hallinan P. W., 1999, Two and Three-dimensional Patterns of the Face
[7]  
Heeger D. J., 1995, Computer Graphics Proceedings. SIGGRAPH 95, P229, DOI 10.1145/218380.218446
[8]  
HUANG J, 1999, P IEEE C COMP VIS PA, V1, P541
[9]  
Huang JG, 2000, PROC CVPR IEEE, P324, DOI 10.1109/CVPR.2000.855836
[10]   CONDENSATION - Conditional density propagation for visual tracking [J].
Isard, M ;
Blake, A .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 29 (01) :5-28