Development of a Computerized Method to Inspect Empty Glass Bottle

Author

Liu, Huan-jun ; Wang, Yao-Nan

Author_Institution

Fac. of Autom., Guangdong Univ. of Technol., Guangzhou, China

Volume

2

fYear

2008

fDate

20-22 Dec. 2008

Firstpage

118

Lastpage

123

Abstract

The objective of this study was to develop a computerized empty glass bottle inspection method in an attempt to replace manual inspection. The inspection system structure based on machine vision was illustrated in the article. Morphologic methods and wavelet transform were used to extract features of the bottle body and the finish from images. The fuzzy support vector machine neural network was adopted as the classifier when the features were extracted. The results of our experiment indicated that it can reach up to 97% of accuracy by using the method developed in this study to inspect empty glass bottles.

Keywords

computer vision; inspection; neural nets; support vector machines; wavelet transforms; computerized empty glass bottle inspection; features extraction; fuzzy support vector machine neural network; inspection system structure; machine vision; manual inspection; morphologic method; wavelet transform; Glass products; Image edge detection; Inspection; Light sources; Lighting; Machine vision; Mouth; Neural networks; Support vector machines; Wavelet transforms; Machine Vision; Morphologic Method; Neural Network; Support Vector Machines; Wavelet Transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Computational Technology, 2008. ISCSCT '08. International Symposium on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-3746-7

Type

conf

DOI

10.1109/ISCSCT.2008.340

Filename

4731585