Augmented Model of Stacked Autoencoder for Image Classification
S N Shivappriya1, Divya Raju2, R. Hari Kumar3
1S N Shivappriya, Department of Electronics and Communication Engineering, Kumaraguru College of Technology, Coimbatore (TamilNadu), India.
2Divya Raju, Department of Electronics and Communication Engineering, Kumaraguru College of Technology, Coimbatore (TamilNadu), India.
3R. Hari Kumar, Department of Electronics and Communication Engineering, Kumaraguru College of Technology, Coimbatore (TamilNadu), India.
Manuscript received on 05 December 2018 | Revised Manuscript received on 12 December 2018 | Manuscript Published on 26 December 2018 | PP: 340-344 | Volume-8 Issue- 2S2 December 2018 | Retrieval Number: BS2076128218/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Stacked Auto Encoder (SAE )is used to pre-train the deep network in the training phase of the individual layer for classifying complex real time data’s. MNIST and IMAGENET are used to train the network. Time consumed and accuracy during the training period is calculated for the MNIST data set which is binary image and IMAGENET dataset includes color image applying the Stacked Auto Encoder algorithm which is trained one layer at a time. Here the SAE consists of three layers which is stacked together and its parameters are varied in such a way that the constructed SAE out performs achieving time and accuracy tradeoff. The SAE model improves the accuracy of the image classifier in both binary and color image dataset with the reduced time.
Keywords: Artificial Neural Network, Stacked, Auto Encoder, Image Classification.
Scope of the Article: Classification