IMAGE PREDICTION USING CONVOLUTION NEURAL NETWORKS WITH HIGH ACCURACY
Choudhary1, Kiran · Zenodo (CERN European Organization for Nuclear Research) · 2019
Image classification is a complex process that may be affected by many factors. There are supervised and unsupervised classification techniques. The emphasis is placed on the deep neural network classification approach and how this technique is used for improving classification accuracy. In this dissertation work we are working on the image prediction using deep learning method. A lot of methods available for the image detection and prediction. Some of the methods are static and some are adaptive methods. We're use convolutional neural networks (CNNs) to perform our task of image detection using deep learning. We're going to try to create a deep learning CNN model for an old Kaggle completion called Dogs vs Cats. There are more than 25000 images of cats and dogs are available for training purpose and 12,500 in the test set that we have to try to label for this dissertation work. Out of which we are using a data set of 2000 samples for training purpose and choose 200 images (100 of each) for testing purpose and finally checked that how our network is performing.