Probabilistic object recognition and localization

Author

Schiele, Bernt ; Pentland, Alex

Author_Institution

Media Lab., MIT, Cambridge, MA, USA

Volume

1

fYear

1999

fDate

1999

Firstpage

177

Abstract

Objects can be represented by regions of local structure as well as dependencies between these regions. The appearance of local structure can be characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This paper presents a technique in which the appearance of objects is represented by the joint statistics of local neighborhood operators. A probabilistic technique based on joint statistics is developed for the identification of multiple objects at arbitrary positions and orientations. Furthermore, by incorporating structural dependencies, a procedure for probabilistic localization of objects is obtained. The current recognition system runs at approximately 10 Hz on a Silicon 02. Experimental results are provided and an application using a head mounted camera is described

Keywords

computer vision; image classification; object recognition; Gabor filters; Gaussian derivatives; dependencies; head mounted camera; local features; local neighborhood operators; local operators; local structure; localization; probabilistic localization; probabilistic object recognition; Gabor filters; Head; Image databases; Image recognition; Object recognition; Position measurement; Robustness; Silicon; Spatial databases; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on

Conference_Location

Kerkyra

Print_ISBN

0-7695-0164-8

Type

conf

DOI

10.1109/ICCV.1999.791215

Filename

791215