In recent works, the illumination estimation based on Retinex is utilized to enhance the image details. However, to enhance the image using illumination estimation without affecting the naturalness with non-uniform illumination is very difficult. The usual algorithms used for illumination estimation failed to include these constraints such as sharp edges on illumination boundaries, spatial smoothness, and the limited range of illumination while preserving the naturalness. In this paper, an illumination estimation algorithm using normalized $$L_2$$-Norm with the joint edge-preservation filter is proposed. The proposed algorithm efficiently estimates illumination and fulfils all the above-mentioned constraints. The normalized $$L_2$$-Norm is used to approximate the illumination to overcome the block effect in patch-wise illumination. Then, the overall structure is refined by using the joint edge-preservation filter. Experimental results show the quality of the smoothness of illumination beyond the edges and ensure the range of the estimated illumination in comparison with the other state-of-the-art algorithms.

中文翻译：

---

使用基于 Retinex 的归一化 $$L_2$$L2-Norm 进行图像增强的非均匀光照估计来保持自然度的另一种方法

在最近的工作中，利用基于 Retinex 的光照估计来增强图像细节。然而，使用光照估计增强图像而不影响非均匀光照的自然度是非常困难的。用于光照估计的常用算法未能包括这些约束，例如光照边界上的锐利边缘、空间平滑度以及在保持自然性的同时光照范围有限。在本文中，提出了一种使用归一化$$L_2$$-Norm 和联合边缘保留滤波器的光照估计算法。所提出的算法有效地估计光照并满足所有上述约束。归一化的 $$L_2$$-Norm 用于近似照明，以克服逐块照明中的块效应。然后，通过使用联合边缘保留滤波器对整体结构进行细化。实验结果表明，与其他最先进的算法相比，边缘以外的照明平滑度的质量，并确保了估计照明的范围。