Appl Opt. 2020 Oct 1;59(28):8628-8637. doi: 10.1364/AO.401792.
Poor visual quality of color retinal images greatly interferes with the analysis and diagnosis of the ophthalmologist. In this paper, we propose an enhancement method for low-quality color retinal images based on the combination of the Retinex-based enhancement method and the contrast limited adaptive histogram equalization (CLAHE) algorithm. More specifically, we first estimate the illumination map of the entire image by constructing a Retinex-based variational model. Then, we restore the reflectance map by removing the illumination modified by Gamma correction and directly enable the reflectance as the initial enhancement. To further enhance the clarity and contrast of blood vessels while avoiding color distortion, we apply CLAHE on the luminance channel in CIELUV color space. We collect 60 low-quality color retinal images as our test dataset to verify the reliability of our proposed method. Experimental results show that the proposed method is superior to the other three related methods, both in terms of visual analysis and quantitative evaluation while testing on our dataset. Additionally, we apply the proposed method to four publicly available datasets, and the results show that our methods may be helpful for the detection and analysis of retinopathy.
低质量的彩色视网膜图像会极大地干扰眼科医生的分析和诊断。在本文中，我们提出了一种基于 Retinex 增强方法和对比度受限自适应直方图均衡化 (CLAHE) 算法的低质量彩色视网膜图像增强方法。更具体地说，我们首先通过构建基于 Retinex 的变分模型来估计整个图像的光照图。然后，我们通过去除由伽马校正修改的光照来恢复反射率图，并直接将反射率作为初始增强。为了在避免颜色失真的同时进一步增强血管的清晰度和对比度，我们在 CIELUV 颜色空间的亮度通道上应用 CLAHE。我们收集了 60 张低质量彩色视网膜图像作为我们的测试数据集，以验证我们提出的方法的可靠性。实验结果表明，与其他三种相关方法相比，我们提出的方法在我们的数据集上进行视觉分析和定量评估时都具有优越性。此外，我们将提出的方法应用于四个公开可用的数据集，结果表明我们的方法可能有助于视网膜病变的检测和分析。
