Optimization method for improving 2D complex edge detection precision

Abstract

The invention discloses an optimization method for improving 2D complex edge detection precision, and the method comprises the steps of selecting a rectangular ROI region from a to-be-processed image,rotating the ROI region to be horizontal, building a coordinate system through employing the central point of the ROI region as an origin of coordinates, calculating the projection gray sum of each row of pixels in the ROI region, and taking the row with the minimum projection gray sum as a black peak row; according to the distance difference Dx and Dy between the center coordinate of the row where the black peak row is located and the center of the original ROI before rotation in the horizontal and vertical directions, mapping the center coordinate of the row where the black peak row is located back to the original ROI, and extracting a plurality of edges with the same attribute in the ROI in combination with the edge attribute; the invention has the advantages that the projection gray scale and the curve are obtained through rotary projection, the image edge attributes are combined, multiple edges with the same attributes in the ROI area are extracted more accurately, the requirement for the camera resolution is reduced, the stability of the algorithm is improved, and meanwhile the characteristic quantity of the edges extracted through the algorithm is increased.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an optimization method for improving the detection accuracy of 2D complex edges. Background technique [0002] In machine vision and image processing, the area to be processed is outlined in the form of rectangles, circles, ellipses, irregular polygons, etc. from the processed image, which is called the region of interest ROI. The region of interest ROI is a selected one from the image. Image area, this area is the focus of image analysis, delineating this area for further processing, using ROI to delineate the target to be read can reduce processing time and increase accuracy. [0003] However, there are still many deficiencies in the existing technology. The existing scheme has three edge attributes in the re-extraction of the edge: the first edge is the top, the position close to the center of the rectangle is near the center line, and the edge strength is the largest....

AI Technical Summary

Problems solved by technology

[0003] However, there are still many deficiencies in the existing technology. The existing scheme has three edge attributes in the re-extraction of the edge: the first edge is the top, the position close to the center of the rectangle is near the center line, and the edge strength is the largest. However, in many complicated cases, When the resolution of the camera is not large enough, there will be multiple edges with the same attribute in the measurement ROI area. For example, if the edge attribute is selected from black to white, there will be multiple edges in the ROI. Therefore, when measuring multiple products, the ROI area There will be deviations, so that the previous 3 attributes will change

Images