The description is submitted to:


Session R4830 ("Can You Read This One?" New Advances and Issues in Digital Recognition of Printed/Handwritten Arabic Characters), 2017
The initial experiment on neural networks by Rosenblatt back in 1958, which inspired artificial intelligence, was actually about trying to capture letters on a screen by a computer. In this roundtable we would like to address the importance of character and pattern recognition methodologies for the computer sciences and their possible implications for historical inquiry. In doing so we will try tackle with questions such as:
Why are computer scientist obsessed with recognition problem? Is it possible to capture scripts with a success rate close to %99? What are the recent developments in Intelligent Character Recognition and their connections with the advances in the fields of machine learning and computer vision? Is there a chance to use mainstream methodologies such as Convolutional and Recurrent Neural Networks. Could hybrid algorithms provide us with better solutions?