• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SIBGRAPI Conference on Graphics, Patterns and Images >Retinal Vessel Segmentation Using Parallel Grayscale Skeletonization Algorithm and Mathematical Morphology
【24h】

Retinal Vessel Segmentation Using Parallel Grayscale Skeletonization Algorithm and Mathematical Morphology

机译：基于并行灰度骨架化算法和数学形态学的视网膜血管分割

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Retinal vessel segmentation is an important step for the detection of numerous system diseases, such as glaucoma, diabetic retinopathy, and others. Thus, the retinal blood vessel analysis can be used to diagnose and to monitor the progress of these diseases. Manual segmentation of fundus images is a long and tedious task that requires a specialist. Therefore, many algorithms have been developed for this purpose. This paper demonstrates an automated method for retinal blood vessel segmentation based on the combination of topological and morphological vessel extractors. Each of these extractors is based on different blood vessel features to increase the detection robustness. The final segmentation is obtained intersecting the two resulting images, smoothing the vessel borders and removing spurious objects remaining. Our proposed method is tested on DRIVE and STARE databases, achieving an average accuracy of 0.9565 and 0.9568, respectively, with good values of sensitivity and specificity.
机译：视网膜血管分割是检测多种系统疾病（例如青光眼，糖尿病性视网膜病等）的重要步骤。因此，视网膜血管分析可用于诊断和监测这些疾病的进展。手动分割眼底图像是一项漫长而乏味的任务，需要专家的协助。因此，已经为此目的开发了许多算法。本文展示了一种结合拓扑和形态血管提取器的视网膜血管自动分割方法。这些提取器均基于不同的血管特征，以提高检测的鲁棒性。最终的分割与两个结果图像相交，平滑了血管边界并去除了残留的虚假物体。我们提出的方法在DRIVE和STARE数据库上进行了测试，平均准确度分别为0.9565和0.9568，并具有良好的灵敏度和特异性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号