Offline handwritten Malayalam character recognition using stacked LSTM

In this paper we propose a model for isolated Malayalam handwritten character recognition using stacked LSTM. Ninty symbols from the Malayalam character set is considered for the recognition and total samples used are 18000. Network consists of two LSTM layers and final output layer for prediction. Accuracy achieved is more than 90 %. Top-2 results shows that it can be improved by addition of more samples in the dataset.

[1]  Binu P. Chacko,et al.  Pre and Post Processing Approaches in Edge Detection for Character Recognition , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[2]  John Jomy,et al.  Pattern Analysis Techniques for the Recognition of Unconstrained Handwritten Malayalam Character Images , 2013 .

[3]  Binu P. Chacko,et al.  Handwritten character recognition using wavelet energy and extreme learning machine , 2012, Int. J. Mach. Learn. Cybern..

[4]  Bidyut Baran Chaudhuri,et al.  Indian script character recognition: a survey , 2004, Pattern Recognit..

[5]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.

[6]  Bidyut Baran Chaudhuri,et al.  A Two Stage Approach for Handwritten Malayalam Character Recognition , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[7]  Alex Graves,et al.  Supervised Sequence Labelling , 2012 .

[8]  Kannan Balakrishnan,et al.  Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier , 2012 .

[9]  Bindu S Moni,et al.  Modified quadratic classifier for Handwritten Malayalam Character recognition using Run Length Count , 2011, 2011 International Conference on Emerging Trends in Electrical and Computer Technology.

[10]  Cheng-Lin Liu,et al.  Modified Quadratic Classifier and Directional Features for Handwritten Malayalam Character Recognition , 2011 .

[11]  Umapada Pal,et al.  Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques , 2012, TALIP.

[12]  M. S. Nair,et al.  A novel handwritten character recognition system using gradient based features and run length count , 2014 .

[13]  K. V Pramod,et al.  Offline handwritten Malayalam Character Recognition based on chain code histogram , 2011, 2011 International Conference on Emerging Trends in Electrical and Computer Technology.