The Electrical and Computer Engineering Department at Boise State University invites you to attend a free public seminar featuring ECE Doctoral Candidate Nishatul Majid.
ABSTRACT | Offline handwriting recognition is a decades-old problem in the field of machine learning and it is still challenging researchers today. There are solutions for various subsets of this problem but not a whole system that can recognize handwritten text. Although popular scripts like Latin receive much more attention than other scripts, there are no unifying frameworks that work for any writing system. This talk presents a simple, intuitive and yet extremely effective design is presented that can handle this problem. The design has been tested with Bangla and Korean and should work for almost any other script.
SPEAKER BIO | Nishatul Majid is in his final year of study as a doctoral candidate in the Electrical and Computer Engineering Department at Boise State University. He completed his bachelor's and master's degrees in applied physics, electronics and communication Engineering at the University of Dhaka in Bangladesh. His research interests lie at the intersection of image processing and machine learning.