Development of a generic structural feature extraction method for printed Gurumukhi and similar scripts
Jaspreet Singh Madan, Roop Sidhu, Dharam Veer Sharma · International Conference on Computing for Sustainable Global Development · 2016
Till date researchers have worked on the various feature extraction and classification techniques for various Indian scripts and have developed many feature extraction methods specific to the scripts. The problem is to develop a generalized set of features that can be easily applied on the input script like Gurumukhi or similar scripts. An approach is to be devised in which the same feature set identified can be applied on various input scripts, rather than adding a new language each time. In this paper, generalized set of structural features have been developed that can be applied on Gurumukhi and similar input scripts. The experimental results demonstrate that fonts with reasonably thick stroke and which are made up of clear lines or curves are detected correctly by the system.