| Summary: | Handwritten Alphabet Recognition can be defined as the way of detecting characters from images of Handwritten language alphabets. This is one of the important problems that can be solved by Convolution Neural Networks (CNN). Recent developments in CNN have made it possible to expand this problem area from English character recognition or Numbers recognition to Regional Languages character recognition, there has not been sufficient studies conducted in the domain of regional languages. This study has attempted to give deep learning approach to Tamil Handwritten Alphabets classification. This article aims to develop 3 models of CNN – THAC-CNN1, THAC-CNN2 and THAC-CNN3 to recognize Tamil Handwritten Alphabets and classify them based on its category. Our proposed models use a combination of benchmark dataset and a customized dataset which totals to over 2800 images of different Tamil alphabets after various data augmentation techniques. The proposed models are compared with a popular image classification pre-trained models - VGG-11 and VGG-16. We use the standard classification metric - accuracy to measure the performance of our proposed models. With our dataset and augmentation techniques, one of our models THAC-CNN1 achieves 97% accuracy on the training dataset and 92.5% accuracy on test dataset as opposed to 72% and 73.5% accuracy on training dataset and test dataset by pre-trained models.
|
|---|