【摘要】 噪声字符识别具有很好的应用前景,也是图像后期处理的基础。基于离散Hopfield神经网络的联想记忆能力,通过修整噪声强度将0～9这10个数字和A～Z这26个大写英文字母正确的识别出来。仿真结果表明,当字符被一定的噪声干扰后,仍具有较好的识别效果。更多还原

【Abstract】 Identification of the noise characters have a good application prospect and it is also the basis for image post-processing.Based on the associative memory ability of discrete Hopfield neural network,and by triming intensity of the noise,ten digitals from 0 to 9 and twenty-six capital letters from A to Z can be identified correctly.The simulation results show that there is a good recognition result after the characters are disturbed by the noise.更多还原