- 20.5 Retinal Images, Analysis of Eye, etc.
- 20.5.1 Eye, Cornea, Corneal Images
- 20.5.2 Optic Disc Location, Optic Disc Detection
- 20.5.3 Retinal Images, Angiography, Blood Vessels in the Eye
- 184.108.40.206 Retinal Microaneurysms, Detection
- 20.5.4 Glaucoma Retinopathy, Retinal Analysis Application
- 20.5.5 Cataracts, Detection, Analysis, Surgery
- 20.5.6 Diabetic Retinopathy, Retinal Analysis Application
- 20.5.7 Macular Degeneration Detection, AMD, Retinal Analysis Application
- 20.5.8 Retinal Images, Optical Coherence Tomography, OCT
can someone teach me how to find optic disc using three channels (RGB) ,shannon information content per channel in the ROI, OD centre using the circular Hough transform
1 view (last 30 days)
i need help with the algorithm that should , automatically: (i) uses the three channels (RGB) of the digital colour image to locate the region of interest (ROI) where the OD lies, (ii) measures the Shannon information content per channel in the ROI, to decide which channel is most appropriate for searching for the OD centre using the circular Hough transform
Image Analyst on 25 Jun 2022
Are you talking about color channel? The blue channel should have the greatest contrast between the retina and the optic disc.
What is your formula for Shannon's information content?
Optic discs are not perfectly circular so I don't know why you want to use hough to assume it's circular instead of just thresholding or using one of the more sophisticated published methods :
In short, you might be able to do (in the simplest possible case but not typical case):
mask = rgbImage(:,:,3) > someThreshold;
mask = bwareafilt(mask, 1); % Take largest blob. Assumes disc is not cut into multiple parts by blood vessels.
% Find Centroid.
props = regionprops(mask, 'Centroid');
xyCenter = props.Centroid
plot(xyCenter(1), xyCenter(2), 'b+', 'MarkerSize', 250); % Plot blue crosshairs at centroid.