Optimised hand-printed character recognition using neural network cascades
暂无分享,去创建一个
The sn-tuple classifier based character recogniser has achieved significantly higher computational efficiency than most other current handwritten character recognisers with similar recognition performance. By combining the sn-tuple classifier with other classifiers, it is possible to further improve recognition rates while retaining its efficiency advantages. In this paper, we present theoretical justification and experimental results to support this development.