Performance Analysis of Gradient Descent Methods for Classification of Oranges using Deep Neural Network

Abstract

Automatic classification of fruits is vital in packing and processing factories. In recent years many paradigms have been proposed to classify fruits from images. Gradient descent, being the backbone of most of the optimizers has been optimized frequently for fast convergence of cost function. In this paper, we have compared and analyzed the performance of the four different optimizers namely Gradient Descent, Stochastic Gradient Descent (SGD), RMSProp and Adam for the classification of oranges. The classifier with SGD with momentum=0.95 is 97.5% accurate in classifying the oranges. Different metrics precision, recall, F1 score, ROC-AUC have been evaluated which confirms the brilliance of the classifier. The trained model can now be used for classifying oranges on the production line in the processing industry.