Publication Type:

Conference Paper


2017 23rd National Conference on Communications, NCC 2017, Institute of Electrical and Electronics Engineers Inc. (2017)





Character recognition, Classification models, Classifier systems, Image pixel value, Low pass filters, Low-pass filtering, Pixels, Recognition accuracy, Recognition systems, Scattering networks, Signal representations, Wavelet decomposition


<p>Feature extraction is the process of mapping input signal to informative representation that can easily be handled by the classifier systems to build decision boundary in between the participating pattern classes. Scattering representation build invariant signal representation by applying a cascade of wavelet decompositions and complex modulus, followed by low-pass filtering. The objective of this paper is to analyze the performance of scattering representation over Malayalam character recognition process. Malayalam character recognizers built from image pixel features and the features extracted from scattering network are tested over real world document images. Soft-max Regression classifier is utilized for building the classification models. Scattering representation based recognition system could achieve a 2% increase in recognition accuracy compared to image pixel value based features. © 2017 IEEE.</p>


cited By 0; Conference of 23rd National Conference on Communications, NCC 2017 ; Conference Date: 2 March 2017 Through 4 March 2017; Conference Code:131493

Cite this Research Publication

K. Manjusha, Kumar, M. A., and Soman, K. P., “Scattering representation in Malayalam character recognition”, in 2017 23rd National Conference on Communications, NCC 2017, 2017.