A mobile phone screen corner detection method based on Hough transform template matching

Abstract

A method for mobile phone screen corner detection based on Hough transform template matching, comprising: 1) using the morphological transformation of the image to preprocess the mobile phone screen area to eliminate interference signals such as noise and moiré; 2) step 1) The image obtained in the image is reduced to a certain scale, and the boundary existing in the image is found out through the edge detection algorithm, and the boundary is voted on using the Hough transform to obtain the straight line segment existing in the picture, and the most suitable four line segments are selected from the set of straight line segments, Make the straight line where four line segments are located can encircle a quadrilateral screen area; 3) to the quadrilateral area gained in step 2), utilize four angles of this quadrilateral to self-adaptively produce corner point template, use this template in quadrilateral Further precise positioning in the area near the vertices, and get the final screen area detection result.

Description

technical field [0001] The invention belongs to the field of object detection and identification, and relates to detecting a specific object from an image, in particular to a method for extracting a screen of a mobile phone. Background technique [0002] There is no clear mathematical definition of the corner point, but it is generally believed that the corner point is the point where the brightness of the two-dimensional image changes sharply or the point where the curvature of the edge curve of the image is the maximum value. These points can effectively reduce the amount of information data while retaining the important features of image graphics, so that the information content is high, effectively improving the calculation speed, which is conducive to reliable image matching, and makes real-time processing possible. Corner points play a very important role in computer vision fields such as 3D scene reconstruction, motion estimation, object tracking, object recognition, ...

AI Technical Summary

Problems solved by technology

The existing technology one is manual extraction, which is time-consuming and labor-intensive, and the effect is not good

The second is to control the camera and only shoot directly at the screen. This requires very high technical requirements for the camera, and it is easy to make mistakes

The third is that the existing technology is not effective and the accuracy is not high

Images