Automatic measurement system and measurement method based on image stitching

Abstract

The invention discloses an automatic measuring system and method based on image splicing. The measuring system mainly comprises a double-axis electric control platform which drives a wiredrawing die to move, a mask engraved with regular patterns, a microscope, an image sensor, a control system which is used for collecting and processing images and controlling displacement of the die, an elevating supporting seat and a pedestal. The measuring method comprises the following steps that a proper stepping shooting scheme is selected according to the aperture size of the wiredrawing die; a calibration board is placed on the electric control platform to calibrate an image collection module; the calibration board is removed, the die and the mask are fixed on the electric control platform, and a control module drives the electric control platform to carry out stepping shooting on the die; and a measuring and processing module carries out angle-point detection, registration, fusion and splicing on image data, and obtains the aperture size of the die via circular fitting operation. Compared to the prior art, the structure is simple, the cost is low, use is convenient, the measuring precision is high and the processing efficiency is high.

Description

technical field [0001] The invention relates to the field of wire drawing die measurement, in particular to a measuring system and a measuring method for measuring the size of an aperture on a wire drawing die by using image splicing technology. Background technique [0002] Image stitching is to stitch a series of partially overlapping images of the same scene into a large, wide-angle, high-resolution image that is close to the original image with little distortion and no obvious seam lines. Corner-based image stitching technology generally includes three parts: corner detection, image registration and image fusion. The quality of image stitching mainly depends on the registration accuracy of images. In actual operation, image stitching needs to detect enough corner points to meet the high-precision image registration requirements. However, the corner points in the existing drawing die measurement are only A small arc obviously cannot meet the high-precision (1um) splicing...

AI Technical Summary

Problems solved by technology

The quality of image stitching mainly depends on the registration accuracy of images. In actual operation, image stitching needs to detect enough corner points to meet the high-precision image registration requirements. However, the corner points in the existing drawing die measurement are only A small arc obviously cannot meet the splicing requirements of high precision (1um)

Images