DocumentCode :
2964547
Title :
Pre-processing Techniques for On-Line Capsule Inspection Based on Machine Vision
Author :
Zhengtao, Zhu ; Liuqian, Huang ; Xiongyi, Yu
Author_Institution :
Sch. of Inf. Eng., Guangdong Univ. of Technol., Guangzhou, China
Volume :
2
fYear :
2011
fDate :
28-29 March 2011
Firstpage :
653
Lastpage :
656
Abstract :
Machine vision has provided great convenience for manufacturing quality inspection. To facilitate on-line capsule inspection base on machine vision, in this paper, a capsule image acquisition system and pre-processing techniques are proposed. Capsule has a cylindrical surface, let it pure rolling on a flat surface, then image it several times during its rolling can make its surface fully visible. As the defect contrasting with capsule is various in different parts, it is needed to segment the capsule image into parts in which the gray values are homogeneous. A method synthesized both local threshold and projection can perform this segmentation quite well. Experiments bear out that this algorithm has good compatibility and the processing time can satisfy on-line inspection.
Keywords :
computer vision; image segmentation; inspection; production engineering computing; quality control; capsule image acquisition system; capsule image segmentation; machine vision; manufacturing quality inspection; online capsule inspection; projection synthesis method; threshold synthesis method; Cameras; Filtering; Image color analysis; Image segmentation; Inspection; Pixel; Surface morphology; Blob Features; Capsule Inspection; Image Segmentation; Local Threshold; Projection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on
Conference_Location :
Shenzhen, Guangdong
Print_ISBN :
978-1-61284-289-9
Type :
conf
DOI :
10.1109/ICICTA.2011.448
Filename :
5750973
Link To Document :
بازگشت