A Study on the Spotting and Recognition of Handwritten Numerals Using Neural Networks

신경망을 이용한 필기체 숫자의 탐지 및 인식에 관한 연구

In this paper, we describe a study on the spotting and recognition of handwritten numerals using neural networks. To recognize a handwritten numeral, two kinds of neural network classifiers ate developed. One makes use of the positive samples only, while the other does both of the positive and negative samples. We propose two numeral spotters which discriminate between numerals and non-numerals. Those are also implemented by using neural networks. From the various experimental results, we found that our methods can be successfully applied to spot and recognize handwritten numerals.