# A Hierarchical Image Matting Model for Blood Vessel Segmentation in Fundus images

arXiv: https://arxiv.org/abs/1701.00892 · HTML: https://mlsanity.com/paper/1701.00892/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2017.

## Built on by (most cited first, 10 of 10)

- [Unsupervised Tissue Segmentation via Deep Constrained Gaussian Network](https://mlsanity.com/paper/2208.02912/) (2022)
- [A new baseline for retinal vessel segmentation: Numerical identification and correction of methodological inconsistencies affecting 100+ papers](https://mlsanity.com/paper/2111.03853/) (2021)
- [Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation](https://mlsanity.com/paper/2501.09947/) (2025)
- [EAR-NET: Error Attention Refining Network For Retinal Vessel Segmentation](https://mlsanity.com/paper/2107.01351/) (2021)
- [Medical Matting: A New Perspective on Medical Segmentation with Uncertainty](https://mlsanity.com/paper/2106.09887/) (2021)
- [IterMiUnet: A lightweight architecture for automatic blood vessel segmentation](https://mlsanity.com/paper/2208.01485/) (2022)
- [3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography](https://mlsanity.com/paper/2210.05104/) (2022)
- [A Novel Solution of Using Mixed Reality in Bowel and Oral and Maxillofacial Surgical Telepresence: 3D Mean Value Cloning algorithm](https://mlsanity.com/paper/2104.06316/) (2021)
- [3D Matting: A Soft Segmentation Method Applied in Computed Tomography](https://mlsanity.com/paper/2209.07843/) (2022)
- [Overview of Deep Learning Methods for Retinal Vessel Segmentation](https://mlsanity.com/paper/2306.06116/) (2023)

## Abstract (arXiv)

In this paper, a hierarchical image matting model is proposed to extract blood vessels from fundus images. More specifically, a hierarchical strategy utilizing the continuity and extendibility of retinal blood vessels is integrated into the image matting model for blood vessel segmentation. Normally the matting models require the user specified trimap, which separates the input image into three regions manually: the foreground, background and unknown regions. However, since creating a user specified trimap is a tedious and time-consuming task, region features of blood vessels are used to generate the trimap automatically in this paper. The proposed model has low computational complexity and outperforms many other state-ofart supervised and unsupervised methods in terms of accuracy, which achieves a vessel segmentation accuracy of 96:0%, 95:7% and 95:1% in an average time of 10:72s, 15:74s and 50:71s on images from three publicly available fundus image datasets DRIVE, STARE, and CHASE DB1, respectively.