본문 바로가기
AI/Computer Vision Materials

5.3 Generalized Hough Transform

by 쵸빙 2020. 8. 7.

In this class, we willl learn about generalized Hough Transform.

 

 

 

 

● Hough Circles

Let's find circles by Hough Transform.

Equation of circle is

Equation of Circle

 

If radius is known, we should consider 2D Hough space and Accumulator array would be A(a, b).

 

 

A point in 2D space becomes a circle in Hough space.

 

 

More points become more circles.

 

If radius is not known, we should consider 3D Hough space.

In this case, the Accumulator array would be A(a, b, r)

 

 

 

● Using Gradient Information

Gradient Information can save lots of computation.

Edge location is (xi, yi) and Edge direction is phi_i.

 

And let's assume radius is known.

 

We need to increment only one point in accumulator.

'AI > Computer Vision Materials' 카테고리의 다른 글

5.2 Hough Transform  (0) 2020.08.05
5.1 Lines Parameterization  (0) 2020.08.05
5.0 Defining Boundaries  (0) 2020.08.05
4.1 Filtering vs Convolution  (0) 2020.08.05
4.0 Image Gradients and Gradient Filtering  (0) 2020.08.04