Palm-Leaf Manuscript Character Recognition and Classification Using Convolutional Neural Networks

In this paper, a character recognition approach using convolutional neural networks with specific focus on Tamil palm-leaf characters has been presented. The convolutional neural network (CNN) used in this paper has utilized around five layers viz., convolution layer, pooling layer, activation layer, fully connected layer, and softmax classifier. The database of character set has been created using scanned images of palm-leaf manuscripts. The database comprises of 15 variety of classes and each class contains around 1000 different samples. The recognition of CNN Classifier if found to be around 96.1% to 100%. The prediction rate is found to be higher due to the large quantum of features extracted for each of the CNN layers. A comparison of the proposed method with other machine learning algorithms has also been presented in the paper.