DocumentCode :
2115567
Title :
Online detection of glass bottle crack based on evolutionary neural network and computer vision
Author :
Tai-shan, Yan ; Xu-Huai, Hu ; Hong-min, Li ; Jia-wei, Zhou
Author_Institution :
Sch. of Inf. & Commun. Eng., Hunan Inst. of Sci. & Technol., Yueyang, China
fYear :
2012
fDate :
21-23 April 2012
Firstpage :
418
Lastpage :
421
Abstract :
Glass bottle detection is a key job of glass enterprises, and crack detection is one of its important aspects. In this study, evolutionary neural network is combined with computer vision and used in online detection of glass bottle crack An online crack detection method for glass bottle based on evolutionary neural network and computer vision is proposed. The detection system includes image collecting module, image processing module, system controlling module, neural network detecting module, machine-electricity performing module and person-machine alternating module. Its ability to learn itself and adapt itself is very powerful due to the application of evolutionary neural network. We can realize a quick and exact online detection of glass bottle crack successfully by this system.
Keywords :
bottles; computer vision; crack detection; evolutionary computation; glass products; image processing; neural nets; production engineering computing; quality control; computer vision; evolutionary neural network; glass bottle crack online detection; glass enterprises; image collecting module; image processing module; machine electricity performing module; neural network detecting module; person-machine alternating module; system controlling module; Cameras; Computer vision; Glass products; Image processing; Light sources; Training; Vectors; Computer Vision; Evolutionary Neural Network; Glass Bottle Crack Detection; Image Collecting; Image Processing; Product Quality;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Consumer Electronics, Communications and Networks (CECNet), 2012 2nd International Conference on
Conference_Location :
Yichang
Print_ISBN :
978-1-4577-1414-6
Type :
conf
DOI :
10.1109/CECNet.2012.6201580
Filename :
6201580
Link To Document :
بازگشت