Sinhala Inscription Character Recognition Model using Deep Learning Technologies

Nowadays archaeology experts put huge effort into extracting meaningful information manually from inscriptions. They take at least one month to identify a character. Characters have evolved into different shapes over the centuries. Archeology experts analyze all these shapes one by one to recognize a character. Reading inscriptions directly using manual procedure would be time-consuming and inefficient due to lack of inconsistency. Therefore, it is required to develop a modern technological solution to recognize ancient Sinhala inscription characters. With the purpose of that, this research mainly focuses on developing a solution using Optical Character Recognition module with information retrieval and storing functionality to recognize ancient Sinhala inscription characters which were mainly used in the century from 10 A.D TO 12 A.D. GIS techniques are used to present a map for inscription site tracking features that facilitate users to visit the locations of inscriptions. Mainly three OCR solutions were developed based on template matching, Artificial Neural Networks and Convolutional Neural Network separately. After evaluating each OCR solution, the best- resulted OCR solution was further implemented to incorporate into the Ancient Sinhala inscription character recognition system.