Stochastic Study on CNN Approach for Classifying Images

Abstract

Recent years have seen a surge in interest in artificial intelligence and computer vision applications, which are essential for many real-time tasks like video summarization, picture retrieval, and image categorization. Convolutional neural networks, which are employed in numerous image processing and computer vision applications, are one of the most popular deep learning techniques. In this study, a CNN model for classifying colour images is proposed. The proposed model was developed using deep learning tools in MATLAB. Additionally, three separate datasets of varying sizes were used to test the suggested model. With the largest dataset, the suggested model produced the highest accuracy, precision, and sensitivity results, which are as follows: accuracy is 0.9924, precision is 0.9947, and sensitivity is 0.9931 when compared to other models.