Application of Image Analysis for Classification of Ripening Bananas

Abstract

ABSTRACT: A computer vision system was implemented to identify the ripening stages of bananas based on color, development of brown spots, and image texture information. Nine simple features of appearance (L*, a*, b* values; brown area percentage; number of brown spots per cm²; and homogeneity, contrast, correlation, and entropy of image texture) extracted from images of bananas were used for classification purposes. Results show that in spite of variations in data for color and appearance, a simple classification technique is as good to identify the ripening stages of bananas as professional visual perception. Using L*, a*, b* bands, brown area percentage, and contrast, it was possible to classify 49 banana samples in their 7 ripening stages with an accuracy of 98%. Computer vision shows promise for online prediction of ripening stages of bananas.