A Fused Feature Extraction Approach to OCR: MLP vs. RBF
This paper is focused on evaluating the capability of MLP and RBF neural network classifier algorithms for performing handwritten character recognition task. Projection profile features for the character images are extracted and merged with the binarization features obtained after preprocessing every character image. The fused features thus obtained are used to train both the classifiers i.e. MLP and RBF Neural Networks. Simulation studies are examined extensively and the proposed fused features are found to deliver better recognition accuracy when used with RBF Network as a classifier.
KeywordsMLP RBF Hybrid Feature Extraction Character Recognition OCR Neural Network
Unable to display preview. Download preview PDF.
- 1.Alginahi, Y.: Preprocessing Techniques in Character Recognition. In: Mori, M. (ed.) Character Recognition, pp. 1–20. InTechopen Publishers (2010) ISBN: 978-953-307-105-3Google Scholar
- 4.Cavalin, P.R., Britto, A.S., Bortolozzi, F., Sabourin, R., Oliveira, L.S.: An implicit segmentation based method for recognition of handwritten strings of characters. In: Proceedings of ACM Symposium on Applied Computing, pp. 836–840 (2006)Google Scholar
- 5.Blumenstein, M., Verma, B., Basli, H.: A Novel Feature Extraction Technique for the Recognition of Segmented Handwritten Characters. In: Proceedings of the 7th International Conference on Document Analysis and Recognition, pp. 137–141. IEEE Computer Society Press, Edinburgh (2003)Google Scholar
- 6.Blumenstein, M., Verma, B.: Analysis of Segmentation Performance on the CEDAR Benchmark Database. In: Proceedings of the 6th International Conference on Document Analysis and Recognition, pp. 1142–1146. IEEE Computer Society Press, Seattle (2001)Google Scholar