
Training the Image Classifier with and without Data Augmentation
Author(s) -
R. Nithya
Publication year - 2020
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit206245
Subject(s) - convolutional neural network , computer science , classifier (uml) , artificial intelligence , pattern recognition (psychology) , training set , contextual image classification , image (mathematics) , deep learning , artificial neural network , activation function , machine learning
The main objective of this paper is to train the image classifier using Convolutional Neural Networks with tensorflow architecture. The proposed paper focus on systematic approaches in classifying the sample set of images using Convolutional Neural Networks. The CNN model with activation function thus classifies the dataset into two categories exactly like human. Thus, the paper highlights the importance of augmentation by comparing their accuracies.