Calibration plate corner discrimination method based on edge features

• Main Authors: YE JINGYANG, CAO LING, LU SHENGLIN
• Format: Patent
• Language: Chinese; English
• Published: 03.01.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention belongs to the technical field of machine vision. The edge feature-based calibration plate corner discrimination method comprises the following steps of S1, in a calibration plate image,solving a series of Harris corners as feature points, setting a sampling radius for the feature points to be discriminated, and obtaining a neighborhood image within the sampling radius by taking feature point coordinates as a center; S2, carrying out Canny edge extraction on the neighborhood image of the current feature point, assuming that n edge points are obtained, and arranging coordinates of the n edge points into an n * 2 matrix which is called as an edge matrix; and S3, performing singular value decomposition (namely SVD decomposition) on the edge coordinate matrix of the current feature point to obtain an SVD feature value vector of the edge coordinate matrix, and recording the SVD feature value vector as (v1, v2), which is called as an edge feature vector. According to the method, judgment can be better