MASK SELECTION FOR IMAGE PROCESSING

There are many techniques for visual inspection. Four of them are (1) Image subtraction, (2) Dimensional verification, (3) Syntactic approach and, (4) Feature Matching [1]. In Feature Matching or Template Matching method, the image to be inspected is scanned and the required features are extracted. Then these features are compared with those defined for the perfect pattern. This method greatly compresses the image data for storage and reduces the sensitivity of the input intensity data. A number of predefined binary templates can be used to extract the necessary features for images to be inspected. There are 28 different 3x3 templates which can be used for this purpose. For many applications some of this mask may be enough to use. The aim of this study is to help to choose an adequate set of masks among the set of all possible 3x3 masks.

Keywords:

Industrial Visual Inspection, Template Matching Image Processing,

PDF

___

Roland, T.C. and Charles, A.H., “Automated visual inspection: A Survey”, IEEE Transac. On Pattern Analysis and Machine Intelligence, Vol. PAMI-4, No.6., 1982.
Aksoy, M.S., G. Cagil., Turker. A., “Numberplate recognition using inductive learning”, Robotics and Autonomous Systems 870, 1-5, 2000.
Ballard, D.H. and Brown, C.M. “Computer Vision”, Prentice-Hall, New Jersey, 1982.
Sevkli, M., Turkyilmaz, A. and Aksoy, M.S. 2002 “Banknote recognition using inductive learning”, Int. Conf. On Fuzzy Syst. And Soft Computational Intelligence in Management and Industrial Eng., FSSCIMIE’02, İstanbul Technical Univ., pp.122-128, Turkey, May 29-31, 2002.
Turkyilmaz, Sevkli, M. and Aksoy, M.S., “Inspection of ceramic tiles using inductive learning”, 2nd Int. Conf. On Responsive Manufacturing ,ICRM-2002, Gaziantep Univ., pp.508-513, Turkey, June 26-28, 2002.
Aksoy, M.S., Torkul, O. and Cedimoglu, I.H., “An Industrial Visual Inspection System That Uses Inductive Learning", Journal of Intelligent Manufacturing, 15, pp.569-574, 2004a.
Aksoy, M.S. “Saudi Banknote Recognition Using Inductive Learning”, Accepted by Second International Industrial Engineering Conference, Riyadh, Saudi Arabia, December 19-21, 2004b.
Aksoy, M.S. “Signature Recognition Using Inductive Learning”, Submitted to Journal of King Saud University, CCIS, Riyadh, Saudi Arabia, 2004c.