基于多尺度top-hat变换的自适应彩色图像增强

针对传统彩色图像增强过程中的过度增强及空间变化所引起的信息丢失现象,在RGB空间提出一种基于数学形态学top-hat算法,以各分量标准差权重比例为调控因子的彩色图像增强方法。首先,提取R、G、B通道多尺度下的亮、暗细节特征,然后利用控制因子对有应用价值的细节特征进行增强,最后组合三个分量,得到增强的目标图像。实验结果表明,该方法能有效增强图像对比度,避免过度增强,且能很好地保持亮度,视觉效果良好。

Adaptive color image enhancement based on multi-scale top-hat transform

Given the problems of excessive enhancement and information loss caused by space change in the processing of color image enhancement, we propose a method to enhance color images in RGB space based on mathematical morphology top-hat algorithm, which utilizes standard deviation weight ratio of each component as the regulatory factor. Firstly, we extract the bright and dark features under multi-scale of R、G、B channels. Secondly, we use control factors to enhance valuable detail features. Finally, we combine the three components to get the enhanced target image. Experimental results indicate that the method can effectively enhance image contrast, avoid excessive enhancement, keep the brightness, and has good visual effect.