Title :
Handwritten Bangla digit recognition using hierarchical Bayesian network
Author :
Xu, Jin-wen ; Xu, Jinhua ; Lu, Yue
Author_Institution :
Dept. of Comput. Sci. & Technol., East China Normal Univ., Shanghai, China
Abstract :
A hierarchical Bayesian network is used for handwritten Bangla digit recognition. Rather than extracted feature vectors, original digit images are used as the network input directly. The network is trained on handwritten samples. And then it¿s tested on untrained images and hand-drawn digits. An average recognition accuracy of 87.5 is achieved. The system exhibits robust invariant recognition with respect to considerable object noise which is quite common in handwritten digits.
Keywords :
Bayes methods; handwritten character recognition; image recognition; handwritten Bangla digit recognition; hierarchical Bayesian network; Bayesian methods; Clustering algorithms; Feature extraction; Handwriting recognition; Inference algorithms; Intelligent systems; Knowledge engineering; Noise robustness; Pattern recognition; Pixel;
Conference_Titel :
Intelligent System and Knowledge Engineering, 2008. ISKE 2008. 3rd International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-2196-1
Electronic_ISBN :
978-1-4244-2197-8
DOI :
10.1109/ISKE.2008.4731093
