Park Chang Soon, Kim Doo Young

The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 3, No. 4, pp. 915-925, Jul. 1996
10.3745/KIPSTE.1996.3.4.915,   PDF Download:

Abstract

In this paper, in order to find effective features which can handle variations in off-line handwritten numerals, we performed a comparative study in various sets of features. Results of experimental performance comparison shows that 4-directional features using contours and features which combined cross distance, cross, mesh and projection features are very effective for off-line handwritten numerals recognition in terms of recognition rates and recognition times. And tin order to surmount limitation of recognition rate by a single neural network, we proposed a modularized neural network using majority voting and reliability factor with complex feature that mix effective features together. In order to verify the performance of the proposed method, the handwritten numeral databases of Concordia University of Canada and Dong-A University of Korea are used in the experiments. With the database of Concorida University, the recognition rate of 97.1%, the rejection rate of 1.5%, the error rate of 1.4% and reliability of 98.5% are abtained; and with the database of Dong-A University, the recognition rate of 98%, the rejection rate of 1.2%, the error rate of 0.8%, the reliability of 99.1% are obtained.

Statistics
Cite this article