Robust and efficient detection of non-lint material in cotton fiber samples

Author

Zhang, Yupeng ; Smith, Philip W.

Author_Institution

Dept. of Electr. & Comput. Eng., Tennessee Univ., Knoxville, TN, USA

fYear

2002

fDate

2002

Firstpage

51

Lastpage

56

Abstract

This paper describes the design of an automated image segmentation system that provides high-resolution measurements of non-lint material, or trash, in cotton samples. Unlike previous trash analysis systems, this platform is able to accurately and precisely quantify the amount of foreign matter present in a sample in the presence of both illuminant degradation and fiber color variations by employing a new Bayesian Weighted K-Means (BWKM) approach to image segmentation. The design of the BWKM algorithm is presented in detail and its performance is verified and compared with other clustering techniques using both synthetic and real imagery.

Keywords

automatic optical inspection; image segmentation; pattern clustering; textile industry; Bayesian Weighted K-Means; automated image segmentation; clustering; cotton samples; high-resolution measurements; image segmentation; image-based trash measurement; market value; nonlint material; trash; Bayesian methods; Clustering algorithms; Cotton; Degradation; Design engineering; Image analysis; Image segmentation; Light sources; Pixel; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Applications of Computer Vision, 2002. (WACV 2002). Proceedings. Sixth IEEE Workshop on

Print_ISBN

0-7695-1858-3

Type

conf

DOI

10.1109/ACV.2002.1182156

Filename

1182156