An Empty Bottle Intelligent Inspector Based on Support Vector Machines and Fuzzy Theory

Author

Liu, Huanjun ; Wang, Yaonan ; Duan, Feng

Author_Institution

Coll. of Electr. & Inf. Eng., Hunan Univ., Changsha

Volume

2

fYear

0

fDate

0-0 0

Firstpage

9739

Lastpage

9743

Abstract

This text studies empty bottle intelligent inspector based machine vision instead of manual inspection. The system structure is illustrated in detail in this paper. The text also presents the method to extract features from images. After extracting feature, the fuzzy support vector machines are used as classifier. A genetic algorithm based on optimization algorithm is simultaneously proposed to confirm the parameters of the fuzzy support vector machines, ensuring that the fuzzy SVMs have good classification ability. The experiments demonstrate that using this method to inspect empty bottles, the accuracy rate may reach above 96%

Keywords

bottles; bottling; computer vision; feature extraction; fuzzy set theory; genetic algorithms; image classification; inspection; knowledge based systems; support vector machines; empty bottle intelligent inspector; feature extraction; fuzzy theory; genetic algorithm; image classification; machine vision; support vector machines; Cameras; Inspection; Light emitting diodes; Light sources; Lighting; Machine intelligence; Machine vision; Mouth; Support vector machine classification; Support vector machines; Fuzzy Theory; Intelligent Inspecting; Machine Vision; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1713895

Filename

1713895