A novel graphic symbolrecognition approach of engineering drawings based on radial basis probabilistic neural networks (RBPNN) is proposed.
基于径向基概率神经网络，提出一种扫描工程图纸图像分割后的图形符号识别方法。
2
In order to extract mathematical expressions(MEs) in scanned Chinese document, a ME identification method based on Chinese character recognition and ME symbolrecognition is proposed.
To improve the efficiency of symbolic recognition and enhance the robustness of identification methods, a symbolrecognition method based on the characteristics of the centroid is presented.