Contrast improvement as well as detail preservation is important for human visualization in image enhancement. Traditional histogram equalization methods are easy to produce over-enhancement results, resulting in the loss of fine details. In order to deal with this problem, this paper proposes an image enhancement scheme (called as global–local image enhancement, GLIE) based on weighted least squares (WLS) for contrast enhancement and structural preservation, which includes the following key parts: First, we employ the WLS method to separate a low-quality image into a base image and a detail image. Then, the base image is enhanced by adaptive gamma correction based on cumulative histogram. Next, the enhanced base image jointing with the original image is used to obtain an enhancement coefficient for correcting details. Finally, the high-quality image is generated by adding the enhanced base and detail images. Experimental results in both qualitation and quantitation verify that the proposed GLIE method is effective, and even is better than the state-of-the-arts.

对比度改进和细节保留对于图像增强中的人类可视化很重要。传统的直方图均衡方法容易产生过度增强的结果，导致细节丢失。针对这一问题，本文提出了一种基于加权最小二乘法（WLS）的图像增强方案（称为全局-局部图像增强，GLIE）用于对比度增强和结构保存，包括以下关键部分：我们采用 WLS 方法将低质量图像分为基础图像和细节图像。然后，通过基于累积直方图的自适应伽马校正来增强基础图像。接下来，将增强后的基础图像与原始图像连接起来，得到用于修正细节的增强系数。最后，通过添加增强的基础图像和细节图像生成高质量图像。定性和定量的实验结果验证了所提出的 GLIE 方法是有效的，甚至优于最先进的方法。