Wear debris analysis is becoming an efficient method for machinery condition monitoring due to the recent development in image analysis techniques. It gives us information about not only the wear mode but also the wear mechanism of a machine component. Five types of debris are produced during the operation of a machine: Sphere, Platelet, Long-thin, Cutting and Chunky. A variety of parameters, related to the identification process of wear debris, can affect the performance of image analysis. This paper presents five numerical features to describe the boundary morphology of a debris. An ratio based methodology using Genetic Algorithms is used for classification. The experimental results indicate that due to the simplicity of proposed features, the classification of debris can be done quite rapidly and accurately.