Title :
Automatic image processing filter generation for visual defects classification system
Author :
Hata, Seiji ; Hayashi, Junichiro
Author_Institution :
Fac. of Eng., Kagawa Univ., Takamatsu
Abstract :
The visual inspection system is used in various production systems. The Visual Inspection System is used to maintain the quality of products. But, there are some defects which are not detected with enough reliability on conventional systems. To meet with the problems, the automatic generation system of best image processing filters which extract the proper characteristics of images for that kind of defects has been introduced to improve recognition rate. The system is designed to generate two kinds of filters to detect the defects with vague edge and widely distributed defect images using neural network method and co-occurrence histogram images. Experiments shows the generated filters get better recognition rate.
Keywords :
filtering theory; image recognition; neural nets; production engineering computing; quality assurance; automatic image processing filter generation; co-occurrence histogram images; neural network; product quality; recognition rate; visual defects classification system; Character generation; Character recognition; Filters; Image edge detection; Image generation; Image processing; Image recognition; Inspection; Maintenance; Production systems; Automatic Generation; Co-occurrence histgram; Image Processing Filters; Neural Network; Visual Inspection System;
Conference_Titel :
Mechatronics, 2009. ICM 2009. IEEE International Conference on
Conference_Location :
Malaga
Print_ISBN :
978-1-4244-4194-5
Electronic_ISBN :
978-1-4244-4195-2
DOI :
10.1109/ICMECH.2009.4957119
