静态图像区域特征角度信息配准仿真研究

Simulation Research on Registration of Region Feature Angle Information of Static Image

对图像特征角度信息的配准,能够有效提高静态图像的特征准确性以及其清晰度。对静态图像区域特征角度信息的配准,需要先对图像进行降噪处理,获得静态图像目标初始特征角度,完成对图像特征角度信息的配准。传统方法构建静态图像尺度空间,采用相对灰度直方图来表征特征角度信息,但忽略了对图像初始特征角度的获取,导致配准精度偏低。提出静态图像区域特征角度信息配准方法。对静态图像进行分割,抑制图像区域背景中同目标区域差异较大区域所形成的噪声。应用特征角度变换将静态图像区域特征转换为特征角度系数,在特征角度变换域分离信号和噪声并完成静态图像降噪处理,接着采用优化后的特征角度系数重建静态图像,在图像域利用形态学方法获得目标初始特征角度,实现静态图像区域特征角度信息配准。实验结果表明,上述方法图像分割结果明确,特征配准率较高。

This paper presents an information registration method of feature angle in static image area. Firstly, we segment static images to suppress the noise formed by region which has large difference with target area in image re- gional background. Secondly, we apply feature angle transformation to change regional characteristics of static image into characteristic angle coefficient. In transformation domain of feature angle, we separate signal and noise, and then complete noise reduction of static image. Moreover, we use the optimized coefficient of feature angle to recon- struct static image. In the image domain, we use morphological method to obtain the initial feature angle of target, so as to realize information registration of regional feature angle of static image. Simulation results can prove that the proposed method has a clear result of image segmentation and a high rate of feature registration.