Surface blemish detection from passive imagery using learned fuzzy set concepts

Author

Gurbuz, Sabri ; Carver, Albrecht ; Schalkoff, Robert

Author_Institution

Dept. of Electr. & Comput. Eng., Clemson Univ., SC, USA

fYear

1997

fDate

12-14 Apr 1997

Firstpage

310

Lastpage

314

Abstract

An image analysis method for real-time surface blemish detection using passive imagery and fuzzy set concepts is described. The method develops an internal knowledge representation for surface blemish characteristics on the basis of “experience”, thus facilitating autonomous learning based upon positive and negative exemplars. The method incorporates fuzzy set concepts in the learning subsystem and image segmentation algorithms, thereby mimicking human visual perception. This enables a generic solution for color image segmentation

Keywords

fuzzy set theory; image colour analysis; image segmentation; knowledge representation; learning by example; visual perception; autonomous learning; color image segmentation; experience; human visual perception; image analysis method; image segmentation algorithms; internal knowledge representation; learned fuzzy set concepts; learning subsystem; negative exemplars; passive imagery; positive exemplars; real-time surface blemish detection; Face detection; Fuzzy sets; Gain measurement; Humans; Image analysis; Image color analysis; Image segmentation; Image texture analysis; Knowledge representation; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Southeastcon '97. Engineering new New Century., Proceedings. IEEE

Conference_Location

Blacksburg, VA

Print_ISBN

0-7803-3844-8

Type

conf

DOI

10.1109/SECON.1997.598700

Filename

598700