Development of Gender Classification and Writer Identification Systems For Offline Handwritten Gurumukhi Text

Abstract

Over the last few years, a good number of laboratories all over the world have been involved in the research on the offline handwritten text. Pattern Recognition is the process of automated recognition of patterns and regularities in the data by using machine learning techniques. The development of the writer identification and gender classification systems based on behavior biometric traits i.e., handwritten text in the Gurumukhi script is the prime objective of this Ph.D. work. The development of a framework for gender classification in Gurumukhi script is a novel achievement in concern with the Indic scripts as previously no recognized work has been available so far and the development for writer identification with large datasets and with improved and enhanced accuracy rate is also a remarkable attempt as compared to state-of-the-art work. Numerous challenging and stimulating applications based on gender classification and writer identification are forensic investigations, criminal detection, questioned documents, signature identification and verification, forgery detection and so on.