An Insight for Cursive Context-Specific Printed Script Recognition

Abstract

The greatest challenge of machine learning problems is to select suitable techniques and resources such as tools and datasets. Despite the existence of millions of speakers around the globe and the rich literary history of more than a thousand years, it is expensive to find the computational linguistic work related to Punjabi Shahmukhi script, a member of the Perso-Arabic context-specific script low-resource language family. This paper presents a deep insight into the related work with summary statistics, advocating the popularity and success of artificial neural networks and related techniques. The paper includes support from recent trends from the authentic sources based on the top-level researchers' feedback including the machine learning frameworks. A comprehensive comparison of the most popular deep learning techniques convolutional neural network and the recursive neural network has been presented for the cursive context-specific scripts of Perso-Arabic nature. The overview of the available benchmark datasets for machine learning problems, especially for the Perso-Arabic group, is added. This paper incorporates essential knowledge contents for the researchers in machine learning and natural language processing disciplines on the selection of algorithms, architectures, and resources.