Image edge detection method and device

Abstract

The invention discloses an image edge detection method and device. The image edge detection method comprises the steps that each pixel point of an image is used as a to-be-detected pixel point, and the following steps are executed on the to-be-detected pixel points, wherein the distance between an RGB value of one to-be-detected pixel point and an RGB value of an adjacent pixel point at a designated position is calculated; the maximum value of the calculated distances is selected; and whether the maximum value is greater than or equal to a preset threshold value is judged, if yes, the to-be-detected pixel point is an edge point, and it not, the to-be-detected pixel point is a non-edge point. Through the image edge detection method and device, the defects that in the prior art, detection of an image edge by use of a grayscale space is seriously influenced by luminance, and it is difficult to recognize images which are in the same color but have different levels of luminance are overcome, an RGB value space is directly used, therefore, a judgment error generated in chromatic aberration due to catering to visual characteristics of a person is avoided, and the edge points of the image are accurately recognized.

Description

technical field [0001] The invention belongs to the field of image recognition, in particular to an image edge detection method and device. Background technique [0002] When detecting the edge of an image in the current image recognition field, the current color space of the image is usually converted into a grayscale space first, and then other operations are performed. The reason is that the grayscale mainly extracts the brightness of the color, and the naked eye is most sensitive to the brightness. And compared to the RGB value space and the YUV color space, which are three-dimensional, the grayscale space is one-dimensional, and the calculations are relatively simple. [0003] But images expressed in gray space also have inherent deficiencies. That is to say, the gray scale emphasizes the brightness, so the same color has great differences in scenes with different brightness. For example, traffic lights are very dazzling bright red at night; but when viewed in the aft...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that in the prior art, when the gray space is used to detect the edge of the image, it is greatly affected by the brightness, and it is difficult to identify the defects of images of the same color but different brightness, and to provide an image edge that can accurately identify the edge of the image Detection method and device

Images