What does canny mean?

Canny is a very popular edge detection algorithm.

Canny edge detection is a very popular edge detection algorithm, which was proposed by John Canny in 1986. It is a multi-stage algorithm, that is, it consists of multiple steps. This paper mainly expounds the principle and implementation process of Canny operator. Generally speaking, the purpose of edge detection is to significantly reduce the amount of image data while preserving the attributes of the original image.

There are many algorithms for edge detection. Although Canny algorithm has a long history, it can be said that it is a standard algorithm for edge detection, and it is still widely used in research. Gaussian filtering is applied to smooth the image in order to remove noise. Non-maximum suppression technique is applied to eliminate false edge detection (not originally, but detected).

At present, there are many commonly used edge detection models:

There are Roberts operator, Prewitt operator, Sobel operator, Canny operator and so on. There is a second-order Laplacian operator. Image edge detection is based on the gradient of the image, and the gradient of the obtained image is transformed into convolution operation between the image and various operators. Therefore, the core of image edge detection algorithm lies in the operator. The edge of Laplace operator is the most complete, clear and uniform, and its edge detection result is obviously better than other algorithms.

When detecting the edge of an image, the edge detection algorithm first roughly detects some pixels of the image contour, then connects those pixels through some connection rules, and finally detects and connects some previously unrecognized boundary points, and removes the detected false pixels and boundary points to form a complete edge.