论文部分内容阅读
文中首先从协同学角度出发 ,提出了一种协同联想记忆分类器 (SAMC)的实现算法。为了验证SAMC算法的有效性 ,针对汽车车牌图像的识别系统 ,构建了一个基于SAMC的解决方案。实验结果表明 ,用SAMC实现算法识别效果好 ,适合于对有噪声的车牌图像的处理 ;该算法训练简单、联想能力强 ,对具有背景噪声和视角引起的图像畸变失真有一定的抗干扰能力 ,识别结果令人满意。
First of all, from the point of view of synergetics, this paper proposes a collaborative associative memory classifier (SAMC) algorithm. In order to verify the effectiveness of the SAMC algorithm, a SAMC-based solution is constructed for the recognition system of vehicle license plate images. The experimental results show that the proposed algorithm can effectively recognize the noisy license plate images with the SAMC algorithm. The proposed algorithm has the advantages of simple training, strong associative ability and anti-interference ability to image distortion caused by background noise and angle of view. The recognition result is satisfactory.