Coupled Parameter Optimization of PCNN Model and Vehicle Image Segmentation

The pulse coupled neural network (PCNN) has good properties for image segmentation. While the segmentation effect significantly depends on the parameter selection of PCNN. Thus, the adaptive parameter choice is important for the PCNN application research. The coupled parameter optimization algorithm based on the coupling characteristics is proposed, which combines the neural calculation principle and characteristics of gray-scale in the image local area. First, the connection weight matrix of the PCNN model is updated in terms of the Hebb rule. Then the correlation strength factor between different regions is adaptively determined by local mean square deviation. Finally, the vehicle images are segmented by the PCNN model with optimized parameters. Compared with traditional PCNN image segmentation, the proposed method increases the coupling strength between neurons and avoids over-segmentation and under-segmentation. The segmentation quality of license plate images on the moving vehicles is improved, which lays a good foundation for the subsequent feature extraction.

摘要脉冲耦合神经网络（Pulse Coupled Neural Network, PCNN）具有良好的图像分割特性，但神经网络参数的选取对分割效果有较大影响，如何自适应地选择网络参数是脉冲耦合神经网络应用研究的重要内容。本文首次从脉冲耦合神经网络的耦合特性出发，结合神经计算原理及图像局部区域的灰度特性，提出了脉冲耦合神经网络耦合参数的优化算法。首先利用Hebb学习规则对脉冲耦合神经网络模型的链接权值矩阵进行更新，然后利用图像局部区域的均方差自适应确定神经元链接强度系数，最后将优化的PCNN模型应用于运动车辆图像分割。通过耦合参数的优化，增强了神经元之间的耦合强度，与传统PCNN的车辆分割结果相比，较好地避免了过分割和欠分割现象，提高了运动车辆图像中车牌区域的分割质量，为后续车辆特征的提取奠定了良好的基础。