Database corpus for Yoruba handwriting
Jumoke Falilat Ajao, Stephen Olatunde Olabiyisi, Elijah Olusayo Omidiora, Oladotun Olusola Okediran, Odetunji Ode Odejobi · International Journal of Applied Pattern Recognition · 2018
Non-availability of Yoruba handwritten database has been a major challenge affecting the validation of the Yoruba handwritten recognition system. This paper presents an offline Yoruba handwritten database corpus for validating Yoruba handwritten word recognition system (YHWR). In this research work, 50 medical pathology words were gotten from medical pathology dictionary. The medical pathology words were translated to their Yoruba equivalence and the translated words were hand written by 200 indigenous literate writers with appropriate diacritic signs. The offline handwritten data were scanned using 300 dpi. The database corpus created; converted the scanned images to different image format, different resolutions and different image sizes, to test the effect of different resolutions, different format and image sizes on Yoruba handwritten recognition system. The digitised images were used to create Yourba handwritten database, which, could be used to validate the handwritten recognition system. The database created is considered a raw data that require some level of preprocessing before it can be used for validating the YHWR system.