Enhancing the Accuracy in the Classification of Images using Convolutional Neural Network Algorithm over Support Vector Machine Algorithm

To classify novel images using the Convolutional Neural Network (CNN) algorithm and assess how accurate it is in comparison to the Support Vector Machines algorithm. Convolutional neural networks (CNNs) are a subset of artificial neural networks with a distinct design that are based on machine learning. Convolutional Neural Networks have achieved cutting edge results in computer vision tasks by using certain characteristics of the visual brain. The dataset needed for Novel image classification is acquired from the Tensorflow website. The applications for cloud computing and the cloud framework’s infrastructures are planned, developed, and put into use. The data sets are imported, and the Convolutional Neural Network Algorithm and Support Vector Machines Algorithm are run through their paces. For two algorithms, there are two categories. There are 547 samples in each category. Accuracy for the supplied inputs is the outcome that is obtained. The results are obtained using the IBM SPSS program. According to the findings, there is a statistically significant difference between the Convolutional Neural Network Algorithm and its accuracy of 91.10 percent. The value is less accurate than Support Vector Machines Algorithm $86.48 \%, p=0.001$ ($\lt 0.05,2$-tailed). The independent sample TTest was performed to find the mean, Standard Deviation, and Standard Error Mean statistical significance between the categories. From this article, on basis of outomes produced in this study, the Convolutional Neural Network Algorithm provides better accuracy over the Support Vector Machines Algorithm