Automatic retinal vessel segmentation method based on non-fluorescent fundus images

A technology for automatic segmentation of retinal blood vessels, which is applied in the field of image processing, can solve the problems of low segmentation efficiency, low segmentation accuracy of tiny blood vessels, and easy adhesion, etc., and achieve the effects of suppressing uneven illumination, improving segmentation effects, and increasing contrast

CN106355599BActive Publication Date: 2019-03-29SHANGHAI JIAOTONG UNIV
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2019-03-29

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a non-fluorescent eye fundus image based automatic segmentation method for retinal blood vessels. The method comprises following steps: step one, an image is preprocessed, blood vessel characteristics are enhanced, and background noise is weakened; step two, morphological characteristics of the retinal image are extracted with a multi-scale linear operator, and a refined blood vessel framework is segmented with two-dimensional Gabor wavelet transform; step three, after the refined blood vessel framework is segmented, the image is subjected to path morphology filtering, the maximum path length is combined with geometrical characteristics of a blood vessel region, and an adjacent map is constructed; step four, a binaryzation process is performed with regional connectivity analysis and a hysteresis threshold technology for auxiliary segmentation of microvessels, and the segmentation is finished. Compared with the prior art, the method has the advantages as follows: the blood vessel location accuracy is higher, the adhesion phenomena are reduced, and a retinal blood vessel network of the eye fundus image is effectively segmented.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of image processing, in particular to an automatic retinal blood vessel segmentation method based on non-fluorescence fundus images. Background technique

[0002] In 1989, Chaudhuri et al. published the first two-dimensional matched filter method in "Detection of blood vessels in retinal images using two-dimensional matched filters". This method assumes that blood vessels are some equal-width line segments, and the width of blood vessels is between 2- 10 pixels, and the gray distribution of the blood vessel cross-section can be approximated by a Gaussian curve. Based on this, 12 Gaussian templates in different directions are constructed to perform matching filtering on the image, and the maximum response result is output as the filtering result. At that time, this method achieved excellent enhancement effects on blood vessels in retinal images, but the disadvantage was that when the image was doped with nois...

Examples

Embodiment

[0047] This embodiment includes the following steps:

[0048] The first step is to preprocess the image to enhance the characteristics of blood vessels and weaken the background noise.

[0049] The preprocessing includes contrast enhancement and retinal border growth.

[0050] Contrast enhancement is mainly based on a contrast-limited adaptive histogram equalization algorithm. The R channel is overexposed and the contrast is low; the brightness of the B channel is low, and blood vessels are difficult to identify; compared with the R and B channels, the contrast between the blood vessels and the background of the G channel image is the highest, and the noise is less. Therefore, we choose the G channel image for subsequent processing. The present invention uses the CLAHE algorithm to improve the local contrast of the G channel image, expecting to present more image details. Compared with the common adaptive histogram equalization method, the characteristic of CLAHE lies in it...