Fruit Quality Analysis and Disease Detection using Deep Learning Techniques

Abstract

Defective fruits are the main reason for worldwide financial catastrophes in agricultural production. It affects both the dependability and quality of the fruits. Post-harvest, quality checking requires a significant amount of time and labor-intensive skill. Automatically identifying fruit quality enables saving time and labor during harvest. Various algorithms have been created using machine learning and image processing methods to detect and categorize fruit quality. A system using Convolutional Neural Networks (CNN) and transfer learning techniques has been developed to enhance the fruit classification process. Two methods are suggested for predicting fruit freshness. One tailored CNN architecture is proposed by modifying the network's parameters to suit the dataset. The second technique utilizes the pre-trained VGG model with transfer learning to assess the freshness of the fruit. The proposed models are capable of differentiating between fresh and spoiled fruit by analyzing the input photos. This research used 70 diverse types of fruit, such as apples, bananas, oranges, and others. The first CNN obtains 98.55% accuracy for heterogeneous fruit dataset while second VGG16 achieves 99.05% accuracy on similar dataset. The plant village global dataset is utilized with various fruit categories. As a result, The VGG16 provides higher accuracy than conventional CNN and other deep learning algorithms.