Premium
Fuzzy machine vision based clip detection
Author(s) -
Mehran Pejman,
Demirli Kudret,
Surgenor Brian
Publication year - 2013
Publication title -
expert systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 38
eISSN - 1468-0394
pISSN - 0266-4720
DOI - 10.1111/j.1468-0394.2012.00641.x
Subject(s) - clips , computer science , truck , fuzzy logic , artificial intelligence , robustness (evolution) , machine vision , automotive industry , computer vision , machine learning , data mining , automotive engineering , biochemistry , chemistry , engineering , gene , aerospace engineering
This paper describes the use of an objective fuzzy approach for fast and accurate vision‐based inspection. An inspection problem faced by a Canadian automotive parts manufacturer is being used as a case study. The problem is related to a vision system that is being operated to confirm the placement of metal fastening clips on a structural member that supports a truck dash panel. The manufacturer was interested in identifying the presence or absence of metal clips inserted by a robot arm. It took the manufacturer over 8 months to tune its commercial machine vision system to detect missing clips and yet the accuracy and efficiency of the system are being questioned. Five different universities across Canada have been working in parallel on this problem over a time span of 2 years. To this end, we developed an efficient fuzzy model after trying various statistical approaches. The proposed model properly identifies all the images in a database containing 1910 images. The robustness of the fuzzy model is confirmed by its strong performance on the entire database.