A Hierarchical Image Matting Model for Blood Vessel Segmentation in Fundus Images

  title={A Hierarchical Image Matting Model for Blood Vessel Segmentation in Fundus Images},
  author={Zhun Fan and Jiewei Lu and Caimin Wei and Han Huang and Xinye Cai and Xinjian Chen},
  journal={IEEE Transactions on Image Processing},
In this paper, a hierarchical image matting model is proposed to extract blood vessels from fundus images. More specifically, a hierarchical strategy is integrated into the image matting model for blood vessel segmentation. Normally, the matting models require a user specified <italic>trimap</italic>, which separates the input image into three regions: the foreground, background, and unknown regions. However, creating a user specified trimap is laborious for vessel segmentation tasks. In this… 

A hierarchical image matting model for blood vessel segmentation in retinal images

In this section, a various levelled picture matting method is utilized to extract veins from fundus pictures by using area highlights of veins and the suggested technique has less count time and performs better than numerous other regulated and solo strategies.

A Robust Segmentation of Blood Vessels in Retinal Images

Simulations on DRIVE and STARE datasets indicate that proposed technique surpasses recent methods in terms of Accuracy (Acc) and is also computationally efficient than most of the recent methods compared therein.

Unsupervised multiscale retinal blood vessel segmentation using fundus images

A rule-based retinal blood vessel segmentation algorithm that implements two multi-scale approaches, local directional-wavelet transform and global curvelet transform, together in a novel manner for vessel enhancement and thereby segmentation, with an edge over other state-of-the-art supervised methods.

U-Net based Multi-level Texture Suppression for Vessel Segmentation in Low Contrast Regions

A novel retinal vessel segmentation algorithm which handles the background vessel-like texture in a sophisticated manner without harming the vessel pixels is proposed.

Improvement of thin retinal vessel extraction using mean matting method

A new mean matting method based on mean correlation is proposed to extract thin blood vessels precisely and has less computational complexity compared to other existing matting methods.

Retinal Blood Vessel Segmentation: A Semi-supervised Approach

An innovative descriptor named Robust Feature Descriptor (RFD) is proposed to describe vessel pixels more uniquely in the presence of pathology to achieve accurate segmentation of blood vessels.

Robust retinal blood vessel segmentation using hybrid active contour model

This study presents a hybrid active contour model with a novel preprocessing technique to segment the retinal blood vessel in different fundus images by calculating a wide range of proven parameters to prove its robustness.

Retinal Blood Vessels Segmentation using ISODATA and High Boost Filter

A robust vessel segmentation algorithm that is efficient enough to segment retinal vessels tree automatically and accurately and outperforms recently published methods in terms of statistical parameters, such as Accuracy, Sensitivity, and Specificity on DRIVE and STARE datasets.



Automated blood vessel segmentation of fundus images using region features of vessels

The proposed algorithm outperforms its competitors when compared with other widely used unsupervised and supervised methods, which achieves a vessel segmentation accuracy of 95.8% and 95.4% on images from two public datasets DRIVE and STARE, respectively.

Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification

The proposed algorithm is less dependent on training data, requires less segmentation time and achieves consistent vessel segmentation accuracy on normal images as well as images with pathology when compared to existing supervised segmentation methods.

Iterative Vessel Segmentation of Fundus Images

A novel stopping criterion is presented that terminates the iterative process leading to higher vessel segmentation accuracy and is robust to the rate of new vessel pixel addition.

General Retinal Vessel Segmentation Using Regularization-Based Multiconcavity Modeling

A novel multiconcavity modeling approach is proposed to handle both healthy and unhealthy retinas simultaneously and shows very attractive performances not only on healthy retinas but also on a mixture of healthy and pathological retinas.

A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images

Results suggest that this method for blood vessel segmentation in fundus images based on a discriminatively trained fully connected conditional random field model is suitable for the task of segmenting elongated structures, a feature that can be exploited to contribute with other medical and biological applications.

Robust Vessel Segmentation in Fundus Images

A method to reduce calculation time, achieve high accuracy, and increase sensitivity compared to the original Frangi method is presented and a new high resolution fundus database is proposed to compare it to the state-of-the-art algorithms.

An iterative optimization approach for unified image segmentation and matting

This paper combines the segmentation and matting problem together and proposes a unified optimization approach based on belief propagation, which is more efficient to extract high quality mattes for foregrounds with significant semitransparent regions.

Leveraging Multiscale Hessian-Based Enhancement With a Novel Exudate Inpainting Technique for Retinal Vessel Segmentation

Experimental results show that the proposed vessel segmentation method outperforms state-of-the-art algorithms reported in the recent literature, both visually and in terms of quantitative measurements.

FABC: Retinal Vessel Segmentation Using AdaBoost

This paper presents a method for automated vessel segmentation in retinal images, and feature-based AdaBoost classifier (FABC) achieved an area under the receiver operating characteristic (ROC) curve of 0.9561, in line with state-of-the-art approaches, but outperforming their accuracy.