摘要
在车辆识别系统中,从图片中定位车辆是一个重要过程,针对这一问题,提出一种目标消噪增强方法,既以图像强度和图像梯度作为约束函数,构造图像平滑函数的最优化方程,将图像处理问题转化为数学问题,采用变量分离和交替优化算法相结合的方式进行求解,并融合改进Retinex算法进行彩色图像增强。实验结果表明,该方法可以保留边缘特征并消除噪声干扰,为精确实现对目标车辆的识别提供帮助。
In vehicle identification system,locating vehicles from complex background images is an important process.In order to solve this problem,a complex background target denoising enhancement method is proposed.The method construct the optimization equation of image smoothing function by using image intensity and image gradient as constraint function.The problem of image processing is transformed into a mathematical problem,the method of combining variable separation and alternate optimization algorithm is combined to solve the problem.The improved Retinex algorithm is used to enhance the color image.Experimental results show that the proposed method can preserve the edge features and eliminate noise interference,thus laying the foundation for accurate identification of target vehicles.
作者
宋建辉
樊思萌
于洋
刘砚菊
SONG Jianhui;FAN Simeng;YU Yang;LIU Yanju(Shenyang Ligong University,Shenyang 110159,China)
出处
《沈阳理工大学学报》
CAS
2019年第4期25-29,共5页
Journal of Shenyang Ligong University
