Statistics of natural image categories

被引:637
作者
Torralba, A
Oliva, A
机构
[1] MIT, Artificial Intelligence Lab, Cambridge, MA 02139 USA
[2] Michigan State Univ, Dept Psychol, E Lansing, MI 48824 USA
[3] Michigan State Univ, Cognit Sci Program, E Lansing, MI 48824 USA
关键词
D O I
10.1088/0954-898X/14/3/302
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we study the statistical properties of natural images belonging to different categories and their relevance for scene and object categorization tasks. We discuss how second-order statistics are correlated with image categories, scene scale and objects. We propose how scene categorization could be computed in a feedforward manner in order to provide top-down and contextual information very early in the visual processing chain. Results show how visual categorization based directly on low-level features, without grouping or segmentation stages, can benefit object localization and identification. We show how simple image statistics can be used to predict the presence and absence of objects in the scene before exploring the image.
引用
收藏
页码:391 / 412
页数:22
相关论文
共 62 条
[1]   WHAT DOES THE RETINA KNOW ABOUT NATURAL SCENES [J].
ATICK, JJ ;
REDLICH, AN .
NEURAL COMPUTATION, 1992, 4 (02) :196-210
[2]  
Baddeley R, 1997, COGNITIVE SCI, V21, P351, DOI 10.1207/s15516709cog2103_4
[3]   Searching for filters with 'interesting' output distributions: An uninteresting direction to explore? [J].
Baddeley, R .
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1996, 7 (02) :409-421
[4]  
Barnard K, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, P408, DOI 10.1109/ICCV.2001.937654
[5]  
Barrow H., 1978, COMPUTER VISION SYST, V2, P2
[6]   The ''independent components'' of natural scenes are edge filters [J].
Bell, AJ ;
Sejnowski, TJ .
VISION RESEARCH, 1997, 37 (23) :3327-3338
[7]   RECOGNITION-BY-COMPONENTS - A THEORY OF HUMAN IMAGE UNDERSTANDING [J].
BIEDERMAN, I .
PSYCHOLOGICAL REVIEW, 1987, 94 (02) :115-147
[8]   COLOR AND SPATIAL STRUCTURE IN NATURAL SCENES [J].
BURTON, GJ ;
MOORHEAD, IR .
APPLIED OPTICS, 1987, 26 (01) :157-170
[9]   Blobworld: Image segmentation using expectation-maximization and its application to image querying [J].
Carson, C ;
Belongie, S ;
Greenspan, H ;
Malik, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (08) :1026-1038
[10]  
Craw I., 1991, BMVC91, P367, DOI [10.1007/978-1-4471-1921-0_52, DOI 10.1007/978-1-4471-1921-0_52]