<![CDATA[Classification of fruit images using machine learning technology has had a significant impact on human life by enabling accurate recognition of various fruits. With the advancements in technology, machine learning architectures have become increasingly diverse and sophisticated, providing enhanced capabilities for fruit image classification. However, previous studies have primarily focused on classifying fruits at a basic level. Therefore, there is a growing need for the development and application of Fruit Image Classification systems within the community, particularly in the field of agriculture. Such applications can play a pivotal role in leveraging technology to benefit the agricultural sector, empowering users to gain satisfaction and knowledge regarding different fruits through the utilization of these applications. In this study, we employ both a conventional Convolutional Neural Network (CNN) architecture and a Residual Network-50 for fruit image classification. To ensure robust performance evaluation, the dataset is divided into training and testing subsets, with fruits categorized into specific classes. Furthermore, identical preprocessing and optimization techniques are applied to both architectures to maintain consistency and fairness during the evaluation process. The results of our classification experiments on a dataset consisting of 17 different fruit classes reveal that the conventional CNN architecture achieves an impressive accuracy of 0.998 (99%) with a minimal loss of 0.009. On the other hand, the Residual Network-50 demonstrates a slightly lower accuracy of 0.994 (99%) but with a slightly higher loss of 0.02. Despite the higher loss, the Residual Network-50's accuracy remains comparable to that of the conventional architecture, showcasing its potential for fruit image classification. By leveraging the power of machine learning and these advanced architectures, fruit image classification systems can provide valuable insights and assistance to users. They can facilitate informed decision-making in various domains, including agriculture, food production, and consumer education.]]>
