Circle Detection via Standard Hough Transform

Find circles with specific radius in a binary image via Standard Hough Transform.

Description

Function uses Standard Hough Transform to detect circles in a binary image.
According to the Hough Transform for circles, each pixel in image space
corresponds to a circle in Hough space and vise versa.
upper left corner of image is the origin of coordinate system.

Example :
[y0detect,x0detect,Accumulator] = houghcircle(Imbinary,r,thresh)

Acknowledgements

This file inspired Parabola Detection Using Hough Transform, Hough Transform For Circle Detection (Gui), and Hough Transform For Circle Detection.

• Required Products: Image Processing Toolbox
• MATLAB release: MATLAB 6.5 (R13)

[Amin Sarafraz]

all the reported bugs are fixed, please let me know if you find any other bug. Thanks. and check out the software section on the Computer Vision Online (http://www.computervisiononline.com/software) for more open source software related to image processing and computer vision

[waspinator]

 

[Mr Smart]

 

[David]

The performance is sensitive to the pre-defined radius.

[varadha raj]

It's nice to read

[smitha deepu]

sir;
pls send me the mat lab coding for creation of bounding box using regionprops.

[Georg Wiora]

Hardly appliable to real problems, because you need to know the exact radius of the circle you are looking for.

[he yi]

do the fair good work.

[ahmed ahmed]

 

[zainal muttaqin]

i want to know algorithm for image processing, now iam starting to experiment

[Jamal Joder]

Nada

[Big Huy]

 

[mcs swami]

 

[Dennis Bush]

If you can let the user set the range of radius, it would be better.

[Peter Bone]

apart from the speed-up of only looking over the range where the sqrt is real, you can also remove the repeated calculations for y01 and y02.

yOffset = sqrt(r^2-(xIndex(cnt)-x0)^2);
y01 = yIndex(cnt) - yOffset;
y02 = yIndex(cnt) + yOffset;

Also, take the r^2 and image size calculations out of the for loop. They only need to be claculated once.

[Joseph Nguyen]

Does not work at all

[anish l]

 

[CJ Taylor]

You should replace your inner loop to look only over the range of value for which your sqrt is real. This will noticably speed up your routine.

low=x-r;
high=x+r;
if (low<1) low=1; end
if (high>size(Imbinary,2)) high=size(Imbinary,2); end
for x0 = low:high
y01 = y-sqrt(r^2-(x-x0)^2);
y02 = y+sqrt(r^2-(x-x0)^2);
y01 = round(y01); y02 = round(y02);
if y01 < size(Imbinary,1) & y01 >= 1
Accumulator(y01,x0) = Accumulator(y01,x0)+1;
end
if y02 < size(Imbinary,1) & y02 >= 1
Accumulator(y02,x0) = Accumulator(y02,x0)+1;
end
end

[Mirko Beccaria]

Semplice e ben fatto,magari andrebbero aggiunte alcune note per spiegare meglio il programma.Comunque complimenti