Hole set detection method and system based on Hough round convolution transformation algorithm

Abstract

The invention provides a hole set detection method based on a Hough round convolution transformation algorithm. The hole set detection method includes the steps that noise in an image is filtered out, and the image is enhanced; the edge of the image is detected; the Hough round convolution transformation algorithm is adopted for processing the image: the two-dimensional image is mapped into three-dimensional space, Hough round convolution transformation is performed on the mapped image and an indicator function of a Hough circular cone, a three-dimensional Fourier transformation of the Hough circular cone is calculated in advance, then a Fourier transformation of the two-dimensional image is calculated, and then the two Fourier transformations are multiplied to obtain an Hough three-dimension Fourier transformation, and an Hough three-dimensional inverse Fourier transformation is calculated; coordinates and radius values of holes are obtained trough calculating peak points in the three-dimensional inverse Fourier transformation. The detection time is short, measuring precision is high, real-time performance is good, calculation complexity is reduced through the improvement in the algorithm, calculation efficiency is improved, and therefore production cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of hole group detection, and relates to a method and system for hole group detection, in particular to a hole group detection method based on a Hough circular convolution algorithm and a system capable of implementing the method. Background technique [0002] Hole set parts have a wide range of applications in industrial products, and its shape and size determine whether it can be better assembled with its corresponding parts or equipment accurately. Therefore, it is of great significance to accurately and comprehensively detect the shape and size of the hole group. At present, there are two main methods for the detection of hole groups: three-coordinate machine measurement and comprehensive gauge detection. The three-coordinate machine measurement and detection can quantitatively detect the position error of the hole group, but it is expensive and has very high operational requirements for the inspection p...

AI Technical Summary

Problems solved by technology

The three-coordinate machine measurement and detection can quantitatively detect the position error of the hole group, but it is expensive and has very high operating requirements for the inspectors

The comprehensive gauge test cannot detect the actual size and shape of the measured hole group, so it can only be used in occasions where the detection error of the hole group is not high

To sum up, there is still a lack of low-cost and high-precision hole group detection methods at present.

Images