Color fundus image cup segmentation method based on multi-feature fusion
A multi-feature fusion, fundus image technology, applied in the field of image processing, can solve the problem of inaccurate initial contour, and achieve the effect of low contrast, high robustness and accuracy
Active Publication Date: 2019-06-07
SHANGHAI NEW EYES MEDICAL CO LTD
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
And by correcting the position and shape of the candidate region of the optic cup, it also overcomes the inaccurate shortcomings of the initial contour updated only based on the brightness features of the optic cup as the vessel bending point
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] The flow chart of the present invention is as figure 1 As shown, firstly, the multi-directional adaptive Gaussian difference filter is used to perform matching filtering on the enhanced and smoothed fundus blood vessels, so as to realize the extraction of blood vessels in the region of interest. Then, on the basis of optic disc segmentation, use fuzzy C-means clustering (FCM) method to extract optic cup candidate area, and then perform ellipse fitting correction on the optic cup candidate area according to the shape and position characteristics of the optic cup to obtain the rough segmentation of the optic cup result. Finally, the corner detection method based on k-cosine curvature is used to locate the capillary bending point, and the rough segmentation result of the optic cup is updated to obtain the final optic cup segmentation result. The specific implementation process of the technical solution of the present invention will be described below in conjunction with t...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a color fundus image cup segmentation method based on multi-feature fusion. The implementation process is: (1) using the fuzzy c-means algorithm (FCM) method to extract the candidate region of the optic cup; (2) fitting and correcting the candidate region according to the shape and position characteristics of the optic cup to obtain The rough segmentation result of the optic cup; (3) Use the vessel features along the cup edge to locate the vessel bending point to update the rough segmentation result of the optic cup to complete the accurate segmentation of the optic cup. This method combines the characteristics of the optic cup itself with the structural features to make the segmentation more accurate. And by correcting the position and shape of the candidate region of the optic cup, it overcomes the shortcoming of the inaccurate initial contour updated only according to the brightness feature of the optic cup as the vessel bending point. The method in this paper adopts an unsupervised learning method, does not require training samples, and is applicable to different databases. Experiments prove that the method in this paper has high robustness and accuracy for images with severe vascular occlusion, low contrast, and uneven brightness.
Description
technical field [0001] The invention belongs to the technical field of image processing, and relates to a color fundus image cup segmentation method based on multi-feature fusion. It can be used for optic cup segmentation of color fundus images. Accurate segmentation of the optic cup has important clinical significance for the early prevention and treatment of glaucoma. It plays an important role in fundus image analysis. Background technique [0002] Glaucoma has been listed by the World Health Organization as the second leading cause of blindness, and it will affect about 80 million people worldwide by 2020. Glaucoma is a chronic eye disease. Although it cannot be completely cured, early detection and treatment can delay the progression of the disease and even prevent blindness. Therefore, early detection and treatment are very important for glaucoma patients. In the fundus photographic examination of glaucoma, the Cup Disc ratio (CDR) is an important detection paramet...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/12G06T7/13G06K9/00G06K9/44G06K9/32G06K9/62G06K9/42
CPCG06T2207/30041G06V40/193G06V10/255G06V10/32G06V10/34G06F18/2321
Inventor 肖志涛耿磊尚丹丹张芳吴骏
Owner SHANGHAI NEW EYES MEDICAL CO LTD