TRANSFER LEARNING BASED YORÙBÁ CHARACTER RECOGNITION SYSTEM

Optical Character Recognition has been saddled with the responsibility of transforming printed or handwritten materials into digital text files for better human understanding and autonomous machine perception. In the global community, numerous works have been proposed and implemented in the computerization of various human languages, nevertheless, microscopic efforts have also been made so as to put Yorùbá Handwritten Character on the map of Optical Character Recognition. Thus, this study presents a Transfer Learning based framework through the use of the AlexNet pre-trained model for the development of offline Yorùbá Handwritten Character Recognition System so as to fill the gaps in the existing knowledge.