Title :
A Codebook Based Background Subtraction Method for Image Defects Detection
Author :
Lianjun Zhang ; Yao Lu ; Mukai Chen ; Wencai Zou
Author_Institution :
Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
Abstract :
Detection of defects in printing is important in precise print industry. The problem is almost equal to detecting the foreground objectives from cluttered background in video surveillance. It has the same problem of background minor motions. The difficulty lies in how to detect the unknown flaws under complicated background effectively. Inspired by the background modeling approaches for moving objects detection, a background modeling method based on Codebook modeling method in defect detection of printed image is suggested in this paper. The wished printing pattern is defined as background and the exceptional flaw pixels are defined as foreground.
Keywords :
object detection; video surveillance; background minor motions; background modeling method; codebook based background subtraction method; codebook modeling method; complicated background; exceptional flaw pixels; foreground objective detection; image defects detection; moving objects detection; print industry; printed image; video surveillance; wished printing pattern; Adaptation models; Brightness; Computational modeling; Image color analysis; Printing; Real-time systems; Robustness; background modeling; clutterd background; codebook; foreground detection; image;
Conference_Titel :
Computational Intelligence and Security (CIS), 2014 Tenth International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4799-7433-7
DOI :
10.1109/CIS.2014.154