• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸°úÇÐȸ Çмú´ëȸ > KSC 2017

KSC 2017

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) An Optimal Filter Method of Transformed Pattern Graphs for Detection of Defective Products
¿µ¹®Á¦¸ñ(English Title)
ÀúÀÚ(Author) Yihuai Liang   Sunghoon Jung   Bonghee Hong  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 02 PP. 1639 ~ 1639 (2017. 12)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¹®³»¿ë
(English Abstract)
Products defect detection is an important part of the manufacturing process. Defect detection systems with fast speed, high accuracy and persistence are much needed. In this paper, we propose an optimal filter method of transformed pattern graphs for defect detection based on a patternmatching strategy. It is still robust while filtering the testing image even without aligning the pattern graph. It mainly includes three processing steps: firstly, process normal images to generate graph matching patterns; secondly, preprocess test images and filter with graph patterns; finally, extract and locate defects. Experimental results on challenging image datasets demonstrate the excellent performance of the proposed algorithm.
Å°¿öµå(Keyword)
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå