Analysis Of Machine Learning Algorithms For Image Classification Review Paper

Abstract

This research aims to use a subset of the CIFAR100 dataset to develop and present an empirical examination of the performance of powerful Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) for object detection. Image datasets, CIFAR10, CIFAR 100, and MINIST image datasets are all common benchmark datasets for testing performance. This research examines the well-known dataset CIFAR 100. Both classifiers' important attributes are combined in the constructed models. The suggested model's algorithm is trained and tested using images from the CIFAR-100 dataset. The CIFAR 100 is made up of 100 different classes, each with 600 photos. CNN and SVM's receptive fields aid in automatically extracting the most identifiable features from these images. The experimental results confirm the effectiveness of the implementation by reaching a maximum recognition accuracy of 0.4919 percent. Results were obtained as maximum accuracy of 0.4817% For the CNN on Coarse Super Label and maximum accuracy of 0.3696% For the CNN on Fine Super Label, while SVM on Coarse Super Label resulted in an accuracy of 0.0795% and SVM on Fine super Label resulted in 0.0285%. According to the results, CNN was able to exceed the benchmark of 39.43% and 24.49%, but SVM was unable to do so.