Distance distribution-based square detecting method in digital image

Abstract

The invention relates to a distance distribution-based square detecting method in a digital image, which comprises the steps: acquiring an image, and inputting the acquired image into a computer; computing the gradient of each pixel point by a gaussian gradient template; computing an edge graph of the image by a Canny edge detection operator; computing a directional line of each edge point by the gradient of each edge point on the edge graph; computing the characteristic length and the characteristic energy of each pixel point in the image to obtain a characteristic length distribution map and a characteristic energy distribution map of the image; under the constraint of a threshold value, detecting a plurality of local maximum value points on the characteristic energy distribution map; confirming a plurality of edge point sets of one square by each local maximum value point and the characteristic length of each local maximum value point; checking and getting rid of the unreasonable edge point sets of the square by the direction information of the edge points; and outputting the edge point sets which form the square. The method can be used for exactly detecting the center and the edge of the square in the image. Compared with the existing method, the method is simpler and easier to realize, and higher in computation efficiency.

Description

technical field [0001] The invention relates to the field of automatic detection of image features in computer vision, in particular to a detection method for squares in digital images. Background technique [0002] Shape detection and recognition play a very important role in the fields of automatic detection, object positioning, image analysis, and computer-aided design. At present, there are many methods for identifying closed geometric figures composed of straight line segments such as polygons. Generalized Hough Transform (GHT) [1] Using the geometric properties of polygons, the detection problem of variable space graphics is transformed into the clustering problem of parameter space, and the direct detection of polygons is realized. Its characteristics are simple and direct, but due to the large amount of calculation, it is generally only suitable for polygon detection with a small number of triangles and equilaterals. Lara, etc. [2] A parallel algorithm is propose...

AI Technical Summary

Problems solved by technology

Barnes et al. [3-5] The proposed method first obtains the edge of the image, and then uses the posterior probability to define the probability density function of the regular polygon according to the geometric characteristics of the regular polygon, and then realizes the detection of the regular polygon in the road sign by calculating the number of sides and the direction deviation of the regular polygon. The calculation of the method is more complex and the amount of calculation is large

Images