DocumentCode :
2590354
Title :
Learning hierarchical models of scenes, objects, and parts
Author :
Sudderth, Erik B. ; Torralba, Antonio ; Freeman, William T. ; Willsky, Alan S.
Author_Institution :
Electr. Eng. & Comput. Sci., Massachusetts Inst. of Technol.
Volume :
2
fYear :
2005
fDate :
17-21 Oct. 2005
Firstpage :
1331
Abstract :
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of features detected by a low-level interest operator. Each object category then has its own distribution over these parts, which are shared between objects. We learn the parameters of this model via a Gibbs sampler which uses the graphical model´s structure to analytically average over many parameters. Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available. We also extend this hierarchical framework to scenes containing multiple objects
Keywords :
feature extraction; natural scenes; object detection; object recognition; feature detection; hierarchical probabilistic model; image database; low-level interest operator; natural scenes; object centered coordinate frame; object detection; object recognition; Computer science; Computer vision; Dictionaries; Graphical models; Image databases; Layout; Object detection; Random variables; Spatial databases; Visual databases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
Conference_Location :
Beijing
ISSN :
1550-5499
Print_ISBN :
0-7695-2334-X
Type :
conf
DOI :
10.1109/ICCV.2005.137
Filename :
1544874
Link To Document :
بازگشت