Application of machine vision technology in geometric dimension measurement of small parts

Abstract

In this paper, the on-line detection of small parts' dimension measurement based on machine vision is designed, and the key technologies, such as image processing, image registration and stitching, edge detection, sub-pixel location analysis, image feature recognition and clustering, and scale measurement based on image involved in the detection of small part dimension are studied. Firstly, based on the actual usage and the characteristics of the algorithm, the feature-based SIFT algorithm was selected to complete the image registration, and the image edge detection algorithm and data processing method were explored. The histogram equalization improves the grayscale distribution of the stitched image and improves the contrast of the image. The median noise filtering algorithm was used to complete the image noise reduction. The false edge was filtered to get the single pixel edge, and the least square method was used to compensate the missing edge pixels and reduce the measurement error. An accurate image registration transformation matrix was obtained. Then, the weighted average fusion algorithm was used to complete the image fusion. The experimental results show that the image stitching algorithm is accurate and effective, and the measurement accuracy of the system meets the performance requirements.

High Precision Visual Dimension Measurement Method with Large Range Based on Multi-Prism and M-Array Coding

“…By using plane mirror combination, biprism or diffraction grating, the two opposite edge regions of the measured object can reach the same camera imaging plane through two different light paths, so as to achieve the purpose of merging light. As shown in Figure 4, area 1 and area 8 are merged in the same camera imaging plane. With the similar combination of 2 7 , 3 6 , 4 10 , 5 9 , all edge imaging can be completed with five cameras.…”

“…To solve the problems of traditional contact manual measurement, some modern instruments such as coordinate measuring instruments, laser scanning measurements, optical microscope observation and measurement, using image processing technology to realize contour scanning, are improved and applied to the dimension measurement of the workpiece. These modern measuring instruments have obvious advantages, such as high precision and high stability, and their measurement accuracy can reach 1 µm or even 0.5 µm [ 1 ]. Using a coordinate measuring instrument (CMM) for contact measurement of the workpiece, the measurement accuracy is high, the stability is strong.…”

Machine vision-based measurement of air compressor crankshaft journal dimensions

“…Li, B. [10,11] used machine vision methods to design and propose a geometric dimensioning system based on images to calculate small parts and shaft parts. Gao L et al [12] proposed an automatic axle measurement method by using the double-beam projection measurement principle and calculating the axle diameter from the data obtained by scanning profile fitting.…”

Computational Metrology for Measuring Industrial Component Dimensions

“…A great number of methods have been developed for the acquisition of object measurements, including size, shape, colour, and texture, in the past few decades (Li, 2018a). Because of the limitless variation of texture patterns and the lack of a formal scientific definition for image texture, Zheng et al claim that there is not yet a perfect procedure for each sort of measurement, especially texture measurements (Zheng et al, 2006).…”