【摘要】 为了解决低照度图像光照不均、对比度较低、细节展现较差的缺点,本研究提出了一种基于光照校正和补偿的低照度图像增强算法。首先将低照度图像进行颜色空间转换,由RGB颜色空间转换到HSV颜色空间,得到H、S、V三个分量,对饱和度分量S进行自适应增强,采用多尺度梯度域引导滤波对亮度分量V进行处理,从而提取图像的光照分量,并对光照分量采用二维自适应Gamma变换进行校正,用Retinex模型将其进行融合得到新的亮度分量。然后用改进的同态滤波算法对合成之后的RGB图像进行光照补偿,提升图像的暗处细节和整体亮度。实验结果表明,该算法不仅解决低照度图像光照不均的问题,提升了图像的对比度和细节,同时也保持了图像原有的自然性,使图像更加符合人眼的视觉效果,图像质量更高。更多还原

【Abstract】 In order to solve the disadvantages of uneven illumination, low contrast and poor detail display of lowillumination images, the low-illumination image enhancement algorithm based on illumination correction and compensation was proposed. Firstly, the low-illumination image was transformed into HSV color space from RGB color space, and three components, H, S and V, were obtained. Then the saturation component S was adaptively enhanced and the brightness component V was processed by multi-scale gradient domain guided filtering, so as to extract the illumination component of the image which was adopted with two-dimensional adaptive gamma transformation. The Retinex model was used to fuse them to obtain a new brightness component. Then, an improved homomorphic filtering algorithm was used to compensate the illumination of the synthesized RGB image, so as to improve the dark details and overall brightness of the image. The experimental results showed that the algorithm not only solves the uneven illumination of low-illumination images, but also improves the contrast and detail of the images, while maintaining the original naturalness of the images, making the images more in line with the visual effects of human eyes and higher in image quality.更多还原