Cocoa beans classification using enhanced image feature extraction techniques and a regularized Artificial Neural Network model

Cut-Test technique employs visual inspection of interior coloration, compartmentalization, and defects of beans for effective classification of cocoa beans. However, due to its subjective nature and natural variations in visual perception, it is intrinsically limited, resulting in disparities in verdicts, imprecision, discordance, and time-consuming and labor-intensive classification procedures. Machine Learning (ML) techniques have been proposed to address these challenges with significant results, but there is still a need for improvement. In this paper, we propose a color and texture extraction technique for image representation, as well as a generalized, less complex Neural Network model, to help improve the performance of machine classification of Cut-Test cocoa beans. A total of 1400 beans were classified into 14 grades. Experimental results on the equal cocoa cut-test dataset, which is the standard publicly available cut-test dataset, show that the novel extraction method combined with the developed Artificial Neural Networks provides a more homogeneous classification rate for all grades, obtaining 85.36%, 85%, 83%, and 83% for accuracy, precision, recall, and F1 measure, respectively. The proposed model outperforms other ML models, such as Support Vector Machines, Decision Trees, Random Forests, and Naïve Bayes, on the same dataset. Additionally, the proposed ANN model demonstrates relatively better generalization when compared with earlier work by Santos on the same dataset. The proposed techniques in this work are robust on the cut-test dataset and can serve as an accurate Computer-Aided Diagnostic tool for cocoa bean classification.