Low-level numerical characteristics and inductive learning methodology in texture recognition

Author

Pachowicz, Peter W.

Author_Institution

Center for Artificial Intelligence, George Mason Univ., Fairfax, VA, USA

fYear

1989

fDate

23-25 Oct 1989

Firstpage

91

Lastpage

98

Abstract

A method for applying inductive learning to the texture recognition problem is proposed. The method is based on a three-level generalization for the description of texture classes. The first step, scaling interface, is to transform local texture features into their higher symbolic representation as numerical intervals. The second step is the incorporation of the AQ inductive learning algorithm in order to find description rules. The third step is to apply the SG-TRUNC method for rule optimization. The medium recognition ratio for this method was over 90%, and all classes of texture were recognized. In comparison, the k-NN pattern recognition method failed to recognize all classes of textures and had a recognition ratio of 83%

Keywords

learning systems; pattern recognition; AQ; SG-TRUNC method; description rules; inductive learning methodology; numerical intervals; pattern recognition method; rule optimization; scaling interface; symbolic representation; texture recognition; three-level generalization; Artificial intelligence; Character recognition; Computer vision; Convolution; Inspection; Machine learning; Machine vision; Object recognition; Optimization methods; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools for Artificial Intelligence, 1989. Architectures, Languages and Algorithms, IEEE International Workshop on

Conference_Location

Fairfax, VA

Print_ISBN

0-8186-1984-8

Type

conf

DOI

10.1109/TAI.1989.65307

Filename

65307