A mobile phone screen mark point positioning method and system

Abstract

The invention discloses a mobile phone screen Mark point positioning method and system. The positioning method comprises: collecting a reference image of a mobile phone screen, selecting a Mark point template image in the reference image, and obtaining a reference template image; carrying out image preprocessing on the reference template image to obtain a four-layer pyramid template image; rotating the four-layer pyramid template image 89 times, each rotation of one degree, to obtain a multi-angle four-layer pyramid template image rotated 0-89 degrees; collect the image to be tested on the mobile phone screen, expand the edge pixels of the image to be tested, and perform image preprocessing on the image to be tested to obtain the image to be tested A four-layer pyramid image; using the normalized cross-correlation matching method to match the multi-angle four-layer pyramid template image with the four-layer pyramid image to be tested, and obtain the position coordinates and template degree with the highest matching degree. Through multi-angle matching, the search range is narrowed layer by layer to determine the angle and coordinates of the Mark point in the image, and the sub-pixel coordinates of the Mark point in the mobile phone screen image can be obtained at the bottom layer.

Description

technical field [0001] The invention relates to the field, in particular to a method and system for locating Mark points on a mobile phone screen. Background technique [0002] The function of the Vision Alignment Platform is to achieve precise alignment between two targets. The vision system needs to take pictures of two targets separately, and select the feature information of the Mark point or the edge or corner of the target. Using the visual alignment technology, realize the deviation between the physical coordinates of two targets in the X, Y axis and angular coordinates. By driving the relevant motion platform, guide the platform to move to the fitting position, and realize the vision-guided precise alignment. [0003] At present, the development of the detection and positioning of Mark points on mobile phone screens in the prior art mainly uses commercial vision library algorithms, such as Halcon and visionPro vision library. The algorithms of commercial vision libr...

AI Technical Summary

Problems solved by technology

The algorithm based on feature points needs to extract the feature points first, and then calculate the coordinates through affine transformation. This processing method has poor robustness and requires high detection of feature points, while the relatively stable feature point detection algorithm takes a long time. , the edge detection algorithm needs to first extract the edge, then calculate the edge matching degree, obtain the maximum matching degree position, and then obtain the sub-pixel coordinates through surface fitting, but the robustness of the edge detection algorithm is poor

Images