Fruit maturity estimation based on fuzzy classification

Abstract

In this paper an efficient approach of fruit maturity classification based on apparent color of the specimen is implemented by the aid of fuzzy inference system (FIS). Heuristically acquired hue and its corresponding saturation and lightness are the attributes of choice, which are utilized to classify the sample into three classes; Raw, Ripe, and Overripe. The membership functions and fuzzy rules required by the Mamdani FIS are estimated by the approach of classification tree. The experimentation is performed upon 200 guava samples. The fuzzy system is trained upon 60% of the dataset, yielding 93.4% classification accuracy.