径向基神经网络算法在车牌字符识别中的应用

提出一种基于径向基网络的汽车车牌字符识别算法.在预处理阶段,采用灰度化、自适应阈值分割去除图像噪声并增强图像对比度;在字符分割阶段,采用极限元素位置确定法实现独立字符分割;在字符识别阶段,利用自行构建的字符子块图像库对径向基神经网络进行训练.选取基于反向传播(BP)神经网络的字符识别算法和基于支持向量机(SVM)的字符识别算法与文中方法进行比较.实验结果表明:文中方法在识别准确率上具有明显优势,更适用于汽车车牌的字符识别.

Application of Radial Basis Function Neural Network Algorithm in License Plate Character Recognition

A vehicle license plate character recognition algorithm based on radial basis function network is proposed. In the preprocessing stage, image noise is removed and the contrast of image is enhanced by adaptive threshold segmentation and grayscale; at the character segmentation stage, using the limit element method to determine the position of independent character segmentation; in the stage of character recognition, the training of the radial basis function neural network is used to construct the character sub block image library. The character recognition algorithm based on back propagation(BP)neural network and the character recognition algorithm based on support vector machine(SVM)are selected, and the method is compared with the method in this paper. Experimental results show that this method has obvious advantages in recognition accuracy, and it is more suitable for vehicle license plate character recognition.