Algebraic feature extraction of image for recognition
Pattern Recognition
International Journal of Computer Vision
Image retrieval method based on entropy and fractal coding
WSEAS TRANSACTIONS on SYSTEMS
Possibilistic evidential clustering
AIKED'09 Proceedings of the 8th WSEAS international conference on Artificial intelligence, knowledge engineering and data bases
Possibilistic pattern recognition in a digestive database for mining imperfect data
WSEAS TRANSACTIONS on SYSTEMS
| Hi-index | 0.00 |
Several applications of quality control refer to a kind of defects that do not have well defined or delimited borders. Wall tiles, pieces of wood or textiles are products where this kind of problem has been observed very often. In terms of production processes, this is the case of spots caused by finish imperfections, failures resulting from corrosion processes, cracks as a consequence of internal breaks or damage from handling or material accumulation as a result of warping, The present paper describes a model which detects defects on the external surface of industrial products, especially those whose borders are indefinite. The model uses pattern recognition procedures. In addition to describing the model, a practical application and the results obtained are described, including an important extension of this work, i.e. the comparison of pieces with standards (defect control by means of matching procedures).