由于多尺度Retinex算法增强后图像存在细节信息减弱和颜色失真等不足，本文提出了一种色调恒定的图像增强算法.在原图像中去掉用多尺度高斯函数估计的光照分量，结合参量自适应的非线性函数调整亮度，依据色调恒定的理论保持增强后图像的颜色.与多尺度Retinex比较的实验结果表明，本文算法更有效，增强后的图像不仅细节清晰，而且色彩自然、不失真且运行速度快.

Because of the traditional Retinex enhancement algorithms suffering from the loss of details and color distortion in the enhanced image, a hue preserving image enhancement algorithm is proposed in this work. Firstly, illuminant component estimated using multi-scale Gaussian filter is removed from input image. Then, a new adaptive non-linear function is introduced to modify illumination. Finally, hue is preserved according to the theroy of hue invariant. Experimental results show that the proposed algorithm is more effective in terms of visual effects, and the enhanced image is not only more detail preserving, but the colour is also more natural and without distortion, compared with other methods such as MSRCR.