Learning structural concept with 3-D information of objects

Author

Dong, Gang ; Yamaguchi, Tomohiro ; Yachida, Masahiko

Author_Institution

Fac. of Eng. Sci., Osaka Univ., Japan

fYear

1994

fDate

29 Nov-2 Dec 1994

Firstpage

332

Lastpage

335

Abstract

A new approach is proposed which learns structural concepts using learning from example, by taking 3D information of objects obtained from stereo vision as input for the system. In order to solve the scale problem in the quantitative representation of 3D information, the concept description language (CDL) is defined which represents the 3D relations of surface pairs of objects qualitatively. This CDL representation also serves as the intermediate description between the quantitative values obtained from the vision process and the abstract symbolic description utilized in the machine learning process

Keywords

computer vision; image representation; learning by example; object recognition; stereo image processing; 3D object information; 3D relations; abstract symbolic description; concept description language; learning from example; machine learning process; quantitative representation; quantitative values; scale problem; stereo vision; structural concept learning; surface pairs; Costs; Image databases; Image recognition; Machine learning; Machine learning algorithms; Object recognition; Solid modeling; Spatial databases; Stereo vision; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems,1994. Proceedings of the 1994 Second Australian and New Zealand Conference on

Conference_Location

Brisbane, Qld.

Print_ISBN

0-7803-2404-8

Type

conf

DOI

10.1109/ANZIIS.1994.396983

Filename

396983