ProgramsView all programs
From the news
- Chancellor Amma Addresses the Parliament of World’s Religions
- Amrita Students Qualify for the European Mars Rover Challenge
Publication Type : Conference Paper
Publisher : International Journal on Document Analysis and Recognition
Source : International Journal on Document Analysis and Recognition, Springer Verlag, Volume 21, Number 3, p.187-198 (2018)
Keywords : Classification (of information), Convolution, Convolutional networks, Convolutional neural network, Deep learning, Handwritten recognition, Learning models, Malayalams, Network architecture, Neural networks, Optical character recognition, Scattering transforms
Campus : Coimbatore
School : School of Engineering
Center : Computational Engineering and Networking
Department : Electronics and Communication
Year : 2018
Abstract : Convolutional neural network (CNN)-based deep learning architectures are the state-of-the-art in image-based pattern recognition applications. The receptive filter fields in convolutional layers are learned from training data patterns automatically during classifier learning. There are number of well-defined, well-studied and proven filters in the literature that can extract informative content from the input patterns. This paper focuses on utilizing scattering transform-based wavelet filters as the first-layer convolutional filters in CNN architecture. The scattering networks are generated by a series of scattering transform operations. The scattering coefficients generated in first few layers are effective in capturing the dominant energy contained in the input data patterns. The present work aims at replacing the first-layer convolutional feature maps in CNN architecture with scattering feature maps. This architecture is equivalent to utilizing scattering wavelet filters as the first-layer receptive fields in CNN architecture. The proposed hybrid CNN architecture experiments the Malayalam handwritten character recognition which is one of the challenging multi-class classification problems. The initial studies confirm that the proposed hybrid CNN architecture based on scattering feature maps could perform better than the equivalent self-learning architecture of CNN on handwritten character recognition problems. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.
Cite this Research Publication : K. Manjusha, M. Kumar, A., and Dr. Soman K. P., “Integrating scattering feature maps with convolutional neural networks for Malayalam handwritten character recognition”, in International Journal on Document Analysis and Recognition, 2018, vol. 21, pp. 187-198.