Open AccessRecognition of Ancient Tamil Characters from Epigraphical inscriptions using Raspberry Pi based Tesseract OCR
Author(s) -
M. Merline Magrina
Publication year - 2021
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit217230
Subject(s) - tamil , optical character recognition , inscribed figure , computer science , artificial intelligence , unicode , artificial neural network , chinese characters , character (mathematics) , pattern recognition (psychology) , speech recognition , image (mathematics) , mathematics , art , geometry , literature
Optical Character Recognition (OCR) is the process of identification of the printed text using photoelectric devices and computer software. It converts the inscribed text on the stones into machine encoded format. OCR is widely used in machine learning process like cognitive computing, machine translation, text to speech conversion and text mining.OCR is mainly used in the research fields like Character Recognition, Artificial Intelligence and Computer Vision. In this research, the recognition process is done using OCR, the inscribed character is processed using Raspberry Pi device on which it recognizes characters using Artificial Neural Network. This work mainly focuses on the recognition of ancient Tamil characters inscribed on stones to modern Tamil characters belong to 9th and 12th century characters. The input image is subjected to gray scale conversion process and enhanced using adaptive thresholding process. The output image is subjected to thinning process to reduce the pixel size of the image. Then the characters are classified using Artificial Neural Network Architecture and the classified characters are mapped to modern Tamil character using Unicode. The Artificial Neural Network has input layer, hidden layer of 15 neurons and output layer of 1 neuron to classify the characters. The accuracy of the constructed system for the recognition of epigraphical inscriptions is calculated. The above process is carried out in raspbian environment using python process.