Classification of Image Dataset using Convolutional Neural Network

The present work proposes a methodology for classifying images accurately, using Convolutional Neural Network and Back-Propagation. In Convolutional Neural Network layers are arranged in a sequence to extract features and then perform classification in single structure. Applying an apparent architecture and vital preprocessing, our result analysis achieved 85.36% accuracy on ASIRRA dataset. Execution of our technique with unique structure is practically analogous to the state-of-the-art obtained by previous strategies without depending on hand-crafted feature extractors.

Keywords: Convolutional Neural Network, Back-Propagation, Deep Learning, Classification

Suggested Citation: Suggested Citation

Gangwar, Krishanveer and Kumar, Vimal and Singh, Ajay Kr. and Sharma, Vijay Kr., Classification of Image Dataset using Convolutional Neural Network (March 9, 2019). Proceedings of 2nd International Conference on Advanced Computing and Software Engineering (ICACSE) 2019, Available at SSRN: https://ssrn.com/abstract=3349594 or http://dx.doi.org/10.2139/ssrn.3349594