Fast continuous edge extraction method for image

Abstract

The invention provides a fast continuous edge extraction method for an image. The fast continuous edge extraction method comprises the steps of: adopting a differential detection operator for carrying out edge detection on an image I, so as to obtain an edge detection result; performing skeleton extraction on the edge detection result to obtain a skeleton extraction result; traversing each pixel point in the skeleton extraction result, if a value of the current pixel point is not zero, counting the number of pixel points with the value not being zero in a nine rectangle grid which takes the current pixel point as the center, marking the current pixel point if the number is 2, and placing the current pixel point into a breakpoint extraction result set; continuing a breakpoint extraction result to obtain a continuation result; expanding the continuation result to a width r; generating an embedded function initial data matrix of a partial differential equation; and solving the partial differential equation by iteration to obtain a continuous edge of the image, so as to obtain an image continuous edge extraction result. The fast continuous edge extraction method can obtain the edge with good continuity in the image processing process, so as to better improve the precision of later image segmentation, measurement, matching and the like.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image rapid continuous edge extraction method. Background technique [0002] Among the existing edge detection methods, differential operator method and level set method are two representative methods: differential detection operator method and Canny operator (John Canny, 'A computational approach to edge detection', IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8, (6), pp.679-698) as a representative, the advantage of this type of method is that the detection speed is fast, and the disadvantage is that the edge detection result contains a "break" part; a typical representative of the level set method Including MCM (Sapiro G. Affine invariant scale space [J]. International Journal of Computer Vision, 1993, 11 (1): 25-44.), etc., the advantage of this type of method is that the edge extraction results are continuous and good, and the...

AI Technical Summary

Problems solved by technology

However, these improvements have failed to fundamentally solve the shortcomings of the two types of methods. Recently, a continuous edge extraction method for images (Jia Di, Dong Na, Meng Xiangfu, Li Sihui. Computer Engineering and Science. 2015, 37 (2) : 384-389) proposed a rapid continuous edge extraction method combining the advantages of the two methods. This method uses a template to detect the fracture position, and expands the circle with a certain radius on the position. When the fracture edge is relatively close , the expansion part can be connected, and then use the MCM model to iteratively solve with the expansion graph as the initial position to obtain continuous edges

Although good experimental results can be obtained, the following problems still exist: 1) When the radius r is used for circular expansion, when the distance between the two fracture edge breakpoints is too far, the value of r needs to be increased, and the increased r The value will lead to errors in the iterative solution of other edges with close distances; 2) MCM uses curvature as the edge stop function of the driving force, without considering the edge gradient stop force and traction force, and cannot obtain the real edge of the image well

In other words, these two problems limit its specific use environment, thereby reducing the practicality

Images