رئوس مطالب
- چکیده
- کلیدواژه ها
- 1. مقدمه
- 2. مقایسه ارتقای رگ خونی و تکنیک های قطعه بندی
- 3. نتایج آزمایشی
- 4. نتیجه گیری
Abstract
Diabetic retinopathy is caused by complications of diabetes, which can eventually lead to blindness. As new blood vessels form at the back of the eye as a part of diabetic retinopathy (DR), they can bleed and blur vision. Detection of these new vessels and their structure in retinal images is very important for diagnosis of diabetic retinopathy. In this paper two different techniques have been compared. First technique uses Gaussian filtering for preprocessing, LoG filtering for enhancement and adaptive thresholding for segmentation purpose. Second technique uses unsharp masking for preprocessing, Gabor wavelet for enhancement and global thresholding for segmentation. The performance of these systems is evaluated on publicly available DRIVE and STARE databases of manually labeled images. Experimental results show that Gabor wavelet method gives best results for vessel enhancement and global threshold gives good results for vessel segmentation in retinal images.
Keywords: adaptive thresholding - Blood vessel - DIABETIC retinopathy (DR) - enhancement - gabor wavelet transform - log filtering - retinal images - Segmentation - unsharp maskingConclusions
The two computerized methods for retinal blood vessel enhancement and segmentation are compared in this paper. The two techniques are evaluated using DRIVE and STARE databases of retinal images. It is concluded that Gabor wavelet and global thresholding technique is better for the vessel enhancement and segmentation respectively as the Gabor wavelet enhances the vessel as well as de noises the image and global thresholding segment all sizes of foreground vessels whether small or large. The other technique using LoG filter for enhancement and adaptive thresholding for segmentation gives less accurate results and the visibility of vessels is less in this technique.