The retinal blood vessels segmentation algorithm is a powerful tool for the early detection of ophthalmic and cardiovascular diseases and biometrics of the automatic tracking system. Accurate segmentation of blood vessels from a retinal image plays a significant role in the prudent examination of the vessels. Therefore, a combined algorithm of a supervised generalized linear model and an unsupervised contrast limited adaptive histogram equalization is proposed in this paper. Using a generalized linear model integrated with multi-scale information by Gabor wavelet transform, the proposed supervised process can extract more prominent features of retinal blood vessels. Besides, the contrast limited adaptive histogram equalization uses the local histogram equalization, which can handle the illumination variation and adjust the enlargement of details. The method is evaluated on a publicly available DRIVE dataset, as it contains ground truth images precisely marked by experts. The segmentation results show that the proposed method can segment the blood vessels accurately.

视网膜血管分割算法是用于眼科和心血管疾病的早期检测以及自动跟踪系统的生物特征识别的强大工具。从视网膜图像正确分割血管在谨慎检查血管中起着重要作用。因此，本文提出了一种监督广义线性模型和无监督对比度受限自适应直方图均衡的组合算法。使用通过Gabor小波变换与多尺度信息集成的广义线性模型，提出的监督过程可以提取出视网膜血管的更多突出特征。此外，对比度受限的自适应直方图均衡使用局部直方图均衡，可以处理照明变化并调整细节的放大。该方法在公开可用的DRIVE数据集上进行评估，因为它包含由专家精确标记的地面真实图像。分割结果表明，该方法可以准确分割血管。