基于加权L_(0)梯度最小化及伪彩色的图像增强技术在超跨声叶栅纹影试验中的应用

Application of weighted L_(0) gradient minimization algorithm and pseudo color image enhancement method in supersonic/transonic cascade schlieren test

在超跨声叶栅纹影灰度图像中,背景噪声和流场特征信息接近,且灰度图像视觉识别度低,影响叶栅主要流场结构的识别信息量和识别准确性。针对叶栅纹影灰度图像噪声特点,提出了基于加权L_(0)梯度最小化算法和伪彩色处理的图像增强方法。将图像沿水平和竖直方向分解,分别应用L_(0)梯度最小化算法去除噪声及平滑图像,并基于HSV颜色空间的伪彩色处理来提高图像分辨率。研究结果表明,所提出的图像增强方法在去除噪声的同时,还能很好地保留流场结构细节信息。伪彩色增强了纹影图像的分辨率,产生了更好的视觉效果,有效提高了纹影图像的判读能力与识别精度。

In the supersonic and transonic cascade schlieren test gray image,the background noise is close to the flow field characteristic information,and the visual recognition of gray image is low,which affects the recognition accuracy of the flow field structure in the cascade.According to the noise characteristics of cas⁃cade schlieren gray image,an image enhancement method based on weighted L_(0) gradient minimization algo⁃rithm and pseudo color processing was proposed.The image was decomposed along the horizontal and vertical directions,and L_(0) gradient minimization algorithm was applied to remove noise and smooth the image respec⁃tively,and the pseudo color processing based on HSV color space was used to improve the image resolution.The results show that the image enhancement method can not only remove the noise,but also retain the de⁃tails of the flow field structure.Pseudo color enhances the resolution of schlieren image and produces better visual effect,which effectively improves the interpretation ability and recognition accuracy of schlieren image.