Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)
- 1999.11a
- /
- Pages.1007-1010
- /
- 1999
Recognition of Unconstrained Handwritten Numerals using Fully-connected RNN
완전궤환 신경망을 이용한 무제약 서체 숫자 인식
Abstract
This paper describes the recognition of totally unconstrained handwritten numerals using neural networks. Neural networks with multiple output nodes have been successfully used to classify complex handwritten numerals. The recognition system consists of the preprocessing stage to extract features using Kirsch mask and the classification stage to recognize the numerals using the fully-connected recurrent neural networks (RNN). Simulation results with the numeral database of Concordia university, Montreal, Canada, are presented. The recognition system proposed in this paper outperforms other recognition systems reported on the same database.
Keywords