Artificial Intelligence Classifiers for sorting Apples based on Watercore

Statistical classification methods, such as the Bayesian classifier, can provide optimal classification but their performance depends heavily on the assumption of normality of the input data. Artificial intelligence (AI) approaches, on the other hand, entail less stringent assumptions about the statistical characteristics of the input data. Hence, the neural network and fuzzy logic classifiers are expected to perform better than the Bayesian classifier for a given data set. This paper describes steps involved in the development of an optimal neural network classifier and a fuzzy classifier for sorting apples using the selected image features as the input variables. Performance of the AI classifiers developed was compared with that of the Bayesian classifier using the same data set. The fuzzy classifier (80%) performed as well as the Bayesian classifier with linear discriminant functions (79%), whereas, the neural classifier performed better (88%).