基于改进加权引导滤波的红外图像增强算法

Infrared image enhancement algorithm based on improved weighted guided filtering

针对红外图像对比度低、细节不清晰等问题,提出一种基于改进加权引导滤波的红外图像增强算法。首先将原图与梯度图叠加构建引导图像;其次利用canny算子修正边缘权重因子实现保边滤波;然后依据模糊理论设计模糊集增强算法增强图像细节信息;最后应用BM3D去除图像噪声,得到最终增强图像。经对比实验验证,该算法可以有效地提升图像对比度、增强细节信息、去除无关噪声,与参考算法相比,平均梯度提升了2.48%~7.47%,信息熵提升了5.19%~9.76%,结构相似性提升了0.85%~2.58%,视觉效果获得明显改善,可以满足实际应用需求。

Aiming at the problems of low contrast and unclear details of infrared images, an infrared image enhancement algorithm based on improved weighted guided filtering is proposed. Firstly, superimpose the original image and the gradient map to construct the guide image;secondly, use the canny operator to modify the edge weight factor to realize the edge-preserving filtering;then design the fuzzy set enhancement algorithm according to the fuzzy theory to enhance the image detail information;finally apply BM3 D to remove the image noise and obtain the final enhancement image. It is verified by comparative experiments that the algorithm can effectively improve image contrast, enhance detailed information, and remove irrelevant noise. Compared with the reference algorithm, the average gradient is improved by 2.48% ~ 7.47%, the information entropy is improved by 5.19% ~ 9.76%, the structure similarity is improved by 0.85% ~ 2.58%, and the visual effect is significantly improved, which can meet the needs of practical application.