Telugu OCR Framework using Deep Learning
This addresses the problem of digitizing Telugu text for users in linguistics and technology, but it appears incremental as it applies existing neural network methods to a specific script.
The authors tackled Optical Character Recognition for the complex Telugu script by developing an end-to-end framework using deep learning, achieving state-of-the-art error rates.
In this paper, we address the task of Optical Character Recognition(OCR) for the Telugu script. We present an end-to-end framework that segments the text image, classifies the characters and extracts lines using a language model. The segmentation is based on mathematical morphology. The classification module, which is the most challenging task of the three, is a deep convolutional neural network. The language is modelled as a third degree markov chain at the glyph level. Telugu script is a complex alphasyllabary and the language is agglutinative, making the problem hard. In this paper we apply the latest advances in neural networks to achieve state-of-the-art error rates. We also review convolutional neural networks in great detail and expound the statistical justification behind the many tricks needed to make Deep Learning work.