摘要
精确的图像配准是超分辨率重建取得成功的前提。为此,针对大多数图像配准算法存在精度低、抗噪声能力差等缺点,提出一种基于纹理特征的图像自动配准方法。首先用Canny边缘检测算子提取裂缝纹理图像,然后用Photoshop图层工具,通过对待配准帧关于参考帧作变换,得到空间几何变换参数,最后用Matlab编程实现待配准帧的缩放、旋转和平移。对配准后的酸蚀岩板裂缝图像,进行超分辨率重建,结果证明,该方法具有抗噪声能力强、配准精度高、易于编程实现等优点,取得了较好的效果。
In order to achieve successful super-resolution image reconstruction,it is critical for image registration to be precise.In view of mostly image registration algorithms are low quality or resisted noise badly and so on.The paper gives an automatic registration method based on textural features.Firstly,extracted the texture image with Canny recognition arithmetic oprators.Secondly,got the space transformation parameters via the transformation of the target frame referring to the reference frame with Photoshop layer tool.Eventually,achieved the zoom,rotation and translation of the target image by programming with Matlab.The reconstruction results with the registrated images of acid rock plate crevice proved that the method is good anti-noise properties,accurately registration,easily programing.
出处
《微型机与应用》
2011年第9期36-38,共3页
Microcomputer & Its Applications
关键词
图像配准
酸蚀岩板裂缝图像
图像纹理
插值重建
image registration
acid rock plate crevice image
image texture
interpolation reconstruction
