Recognition of Handwritten Numerals Using a Combined Classifier with Hybrid Features
Off-line handwritten numeral recognition is a very difficult task. It is hard to achieve high recognition results using a single set of features and a single classifier, since handwritten numerals contain many pattern variations which mostly depend upon individual writing styles. In this paper, we propose a recognition system using hybrid features and a combined classifier. To improve recognition rate, we select mutually beneficial features such as directional features, crossing point features and mesh features, and create three new hybrid feature sets from them. These feature sets hold the local and global characteristics of input numeral images. We also implement a combined classifier from three neural network classifiers to achieve a high recognition rate, using fuzzy integral for multiple network fusion. In order to verify the performance of the proposed recognition system, experiments with the unconstrained handwritten numeral database of Concordia University, Canada were performed, producing a recognition rate of 97.85%.
KeywordsFeature Vector Recognition Rate Feature Extraction Method Recognition Result Fuzzy Measure
- 2.Soo, R.G., Sung Il, C.: Recognition of Handwritten Numerals by Relearning Hidden Layer Outputs of Modular Neural Nertworks. Korea Information Science Society 23(9), 931–939 (1996)Google Scholar
- 6.Mohiuddin, K.M., Mao, J.: A Comparative Study of Different Classifiers for Handprinted Character Recognition. Pattern Recognition in Practice IV, 437–448 (1994)Google Scholar
- 8.Huang, Y.S., Suen, C.Y.: A Method of Combining Multiple Experts for The Recognition of Unconstrained Handwritten Numerals. IEEE Trans. PAMI 17(1) (1995)Google Scholar
- 9.Cho, S.B., Kim, J.H.: Multiple Network Fusion Using Fuzzy Logic IEEE Trans. Neural Networks 6(2), 487–501 (1995)Google Scholar
- 10.Lee, S.W., Kim, Y.J.: Multiresolution Recognition of Handwritten Numerals with Wavelet Transform and Multilayer Cluster Neural Network. In: 3rd international conference on document analysis and recognition, pp. 1010–1031 (1995)Google Scholar