Title :
A Machine Vision Intelligent Inspector for Injection
Author :
Zhou, Bowen ; Wang, Yaonan ; Ge, Ji ; Zhang, Hui
Author_Institution :
Dept. of Electron. & Inf. Eng., Hunan Univ., Changsha
Abstract :
A machine-vision-based intelligent Inspector for injection is presented. The rotating detection wheel mechanical structure and electric control system based on motion card and data I/O card are illustrated in detail. The inspection flow and optical structure are described. A method using the high-speed camera is applied for obtaining the image sequences. The second-order difference and accumulative energy method are used for identifying the small moving targets. Finally, the arithmetic of separate bubbles and foreign substances based on support vector machine (SVM) is proposed. It can accurately determine whether there are tiny foreign substances in injection. The experiments demonstrate that the detection algorithm is effective and the device of inspector is feasible.
Keywords :
computer vision; image motion analysis; image sequences; support vector machines; SVM; data I-O card; electric control; high-speed camera; image sequences; inspection flow; machine vision intelligent inspector; motion card; optical structure; support vector machine; wheel mechanical structure; Control systems; High speed optical techniques; Image motion analysis; Inspection; Machine intelligence; Machine vision; Motion control; Motion detection; Support vector machines; Wheels;
Conference_Titel :
Computational Intelligence and Industrial Application, 2008. PACIIA '08. Pacific-Asia Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3490-9
DOI :
10.1109/PACIIA.2008.276
