A Genetic Fuzzy Classifier System for Automatic Unhealthy Detection in Texture Images of Poultries in Slaughter Houses

This paper describes a new engineering application of fuzzy logic for automatic unhealthy detection of poultries in slaughter houses. A new approach based on genetic fuzzy classifier for classification of textural images is developed that is enough fast for real time processing. In the presented method, after segmentation of the image into the object (poultry) and background, the size (area), shape (elongation) and the color of the object are calculated as features. Then, these crisp values are converted to their normalized fuzzy equivalents, between 0 and 1. A fuzzy rule base system is then used for inferring that the poultry is normal or not. The parameters of the fuzzy rule based system were optimized using genetic algorithm. Finally, if the output of the fuzzy system shows abnormality, it means that the poultry has some kind of disease and should be omitted form the slaughter. Experimental results show the effectiveness of the proposed method.

کلیدواژه ها:

fuzzy classifier ، classification ، slaughter house ، poultry ، genetic algorithm