MANUSCRIPT ANALYSIS AND EVENT EXTRACTION USING NATURAL LANGUAGE PROCESSING AND CONVOLUTIONAL NEURAL NETWORKS

Abstract

The proposed system explained in this paper, deploys Natural Language Processing which intents to process and understand native and natural languages in penned form. Here we designed  a system to perceive characters and words in unformatted style to a formatted pattern similar to that of a Character Recognition structure. With the aim of finding the combination of feature extraction methods for character recognition of  Tamil dialects and scripts, we present, in this paper, our experimental study on feature extraction methods for character recognition on pre civilization manuscripts. We investigated and evaluated the performance of 10 feature extraction methods and we proposed the proper and robust combination of feature extraction methods to increase the recognition rate. This system will be conducive to read age-old transcripts, manuscripts etc. and shape them into present-day dialect for people to have an easy interpretation and analysis of the pre-civilization period.