Need some advice or hint!
in [Matlab]
|
Prev: Load m-file
Next: Password Entry Using Inputdlg
From: wilson on 10 Dec 2009 15:18 How can i do based on the picture: http://www.merl.com/projects/images/irisrecognition.jpg How can i get the boundry of the iris and the retina? How can i create the cricle on that?I try using hough transform but i can't manage to get the circle! I am just a beginner learner so i need some advice!
From: ImageAnalyst on 10 Dec 2009 21:36 It's not super robust but it works with this image. You can tweak it a bit to make it more robust (work with different colored eyes, etc.) Be sure to fix line breaks introduced by the newsreader. % Demo to outline the iris. % by ImageAnalyst clc; close all; clear all; subplot(2,2,1); rgbImage = imread(irisrecognition.jpg'); imshow(rgbImage); title('Original Image'); set(gcf, 'Position', get(0,'Screensize')) subplot(2,2,2); redPlane = rgbImage(:,:,1); thresholdValue = 119; binaryImage = redPlane < thresholdValue; % Dark objects will be the chosen if you use <. imshow(binaryImage, []); title('Thresholded the Red Channel'); % Do a "hole fill" to get rid of any background pixels inside the blobs. binaryImage = imfill(binaryImage, 'holes'); % Get rid of blobs less than 800 pixels in area. binaryImage = bwareaopen(binaryImage, 20000); subplot(2,2,3); imshow(binaryImage, []); title('Just the iris'); % Do connected componenets labeling. labeledImage = bwlabel(binaryImage, 8); % Label each blob so we can make measurements of it % Get all the blob properties. Can only pass in original image in version R2008a and later. blobMeasurements = regionprops(labeledImage, redPlane, 'all'); numberOfBlobs = size(blobMeasurements, 1); fprintf(1,'Blob # Mean Intensity Area Perimeter Centroid \n'); for k = 1 : numberOfBlobs % Loop through all blobs. % Find the mean of each blob. (R2008a has a better way where you can pass the original image % directly into regionprops. The way below works for all versions including earlier versions.) thisBlobsPixels = blobMeasurements(k).PixelIdxList; % Get list of pixels in current blob. meanGL = mean(redPlane(thisBlobsPixels)); % Find mean intensity (in original image!) meanGL2008a = blobMeasurements(k).MeanIntensity; % Mean again, but only for version >= R2008a blobArea = blobMeasurements(k).Area; % Get area. blobPerimeter = blobMeasurements(k).Perimeter; % Get perimeter. blobCentroid = blobMeasurements(k).Centroid; % Get centroid. fprintf(1,'#%d %18.1f %11.1f %8.1f %8.1f %8.1f\n', k, meanGL, blobArea, blobPerimeter, blobCentroid); end subplot(2,2,4); imshow(rgbImage); % Display it as if it were a perfect circle. equivCircularDiameter = 2 * sqrt(blobMeasurements(1).Area / pi); xcenter = blobMeasurements(1).Centroid(1); ycenter = blobMeasurements(1).Centroid(2); leftColumn = xcenter - equivCircularDiameter/2; topRow = ycenter - equivCircularDiameter/2; set(gca, 'units', 'pixels'); rectangle('Position', [leftColumn,topRow,equivCircularDiameter,equivCircularDiameter],'Curvature', [1,1], 'linewidth', 5, 'EdgeColor', [0 1 0]) title('Image with iris outlined in green');
From: wilson on 10 Dec 2009 21:52 ImageAnalyst if i wanna use this image http://images.google.co.uk/imgres?imgurl=http://salmaworld.files.wordpress.com/2009/09/beautiful-face-wallpapers_11213_1280x1024.jpg&imgrefurl=http://www.mathworks.co.uk/matlabcentral/newsreader/search_results%3Fsearch_string%3Drgb2gray%26view%3Dtext&usg=__MNo8LkQe-DN9sfH4e5E7n5evko0=&h=1024&w=1280&sz=181&hl=en&start=74&itbs=1&tbnid=Drqc8jryXDj1gM:&tbnh=120&tbnw=150&prev=/images%3Fq%3Dface%26gbv%3D2%26ndsp%3D18%26hl%3Den%26sa%3DN%26start%3D72 I wan to find the boudry of iris and retina so how to do it? Just want the circle of the 2 blob like show in http://www.merl.com/projects/images/irisrecognition.jpg. How to draw out the 2 circle by using matlab?
From: wilson on 10 Dec 2009 21:57 i'm using matlab 7.1 so i cant manage to run the program right?
From: ImageAnalyst on 10 Dec 2009 22:27
On Dec 10, 9:52 pm, "wilson " <wilson_silver3...(a)hotmail.com> wrote: > ImageAnalyst if i wanna use this image.... ----------------------------------------------------------------------- Then why did you tell me the other one? Algorithms that work on giant round irised won't necessarily work on small tiny irises. Anyway I've probably spent more time developing code for you than anyone else here. You should be able to handle it from here on out. Please upgrade to the latest MATLAB since I can't be aware of what versions various functionality came into existence. All I know is what I have and that is release R2009b, which is the latest right now. |