Deeper into image classification

Abstract

Recognizing images was a challenging task a few years back. With the advancement of technology and the introduction of deeper neural networks, the issue of recognizing images is solved to a large extent. Inspired by the performance of deep learning models in image classification, the present paper proposed three techniques and implemented that for image classification. The residual network, convolutional neural network, and logistic regression were used for classification. The neural networks have shown the state-of-the-art results in the classification of images. In the implementation of these models, some modifications are made to build a deep residual network and convolutional neural networks. On testing, the ResNet model gave 98.49% accuracy on MNIST and 87.31% on Fashion MNIST. CNN model gave 98.73% accuracy on MNIST and 87.38% on Fashion MNIST. Logistic regression gave 91.79% on MNIST and 83.74% on Fashion MNIST.