基于多感知特征计算的沙尘图像增强算法

Enhancement algorithm of dust image based on multi-perceptual feature calculation

沙尘天气的日益增多严重影响了获取图像的质量,相对于晴朗天气下获取的图像,沙尘图像存在清晰度和亮度偏低、色调偏黄等低质图像特点,已有的图像增强算法并不能完全解决这些问题.针对上述问题,提出了一种基于多感知特征计算的沙尘图像增强算法.首先,利用伽马校正解决由于固体颗粒导致图像亮度偏低的问题;其次,通过动态阈值法校正沙尘图像色调偏黄的问题;最后,利用所提改进去雾算法提高图像的对比度.实验对比结果表明,所提算法利用多个特征增强不同程度的沙尘图像,保留较多的图像细节,校正图像的色偏问题,大幅度提高了图像的对比度,对沙尘图像增强效果明显.

The day by day increased dust weather has seriously affected the quality of acquired images. Compared with images obtained in sunny day, the dust images have some obvious problems such as low quality in brightness and contrast, hue yellowing and so on. In order to solve these problems which cannot be solved completely by the image enhancement algorithms available. Aimed at fore going problems, an image enhancement algorithm is presented based on the multi perceptual feature calculation. Firstly, the gamma correction is used to solve the lower brightness problem caused by solid particles in dust, then the automatic white balance method is employed to correct image hue, and finally, utilizing the proposed defog algorithm, the image contrast is enhance. The experimental result shows that by using the proposedalgo rithm with multiple features, the dust image will be enhanced to some extent, keeping more image details, resolving the contrast and hue correction problems and improving the image contrast to a great extent. This algorithm will have obvious effect for image enhancement.