Tamil Vowel Recognition With Augmented MNIST-like Data Set

06/09/2020

∙

by   Muthiah Annamalai, et al.

∙

0

∙

share

We report generation of a MNIST [4] compatible data set [1] for Tamil vowels to enable building a classification DNN or other such ML/AI deep learning [2] models for Tamil OCR/Handwriting applications. We report the capability of the 60,000 grayscale, 28x28 pixel dataset to build a 92 82 also report a top-1 classification accuracy of 70 accuracy of 92