Sub-pixel shaft part size measurement method based on adaptive threshold

Abstract

The invention discloses a sub-pixel shaft part size measurement method based on a self-adaptive threshold value, and relates to a size measurement method. Calibrating a visual system to obtain internal and external parameters and a mutual position relation; preprocessing the collected image, and improving a gamma correction algorithm by combining a gray histogram to realize automatic selection of a gamma value; completing edge detection, and recording a pixel-level edge position by adopting a Canny operator edge detection method; based on neighborhood edge connection, checking all edge pixel points of the image to complete edge connection; carrying out region extraction based on contour tracking, and converting the binary image into contour description by adopting a contour tracking algorithm with topological structure analysis capability; performing sub-pixel edge detection based on an adaptive threshold, dividing an image region for edge detection, and adaptively selecting a threshold of sub-pixel edge detection; and size calculation: solving the size of the straight line included angle. The precision and the efficiency are higher, the manpower is saved, and the adaptability to the measurement environment is strong.

Description

technical field [0001] The invention relates to a size measurement method, in particular to a sub-pixel shaft part size measurement method based on an adaptive threshold, which belongs to the technical field of robot vision detection. Background technique [0002] In industrial production, the geometric quantity measurement of parts is a necessary means of product quality management and a key link in part processing. Each part must be accurately measured to determine whether it is qualified. The test results not only affect the parts Whether it is qualified or not also determines the subsequent reprocessing of the parts and the overall assembly. Therefore, measurement technology occupies an extremely important position in industrial production, and the research on measurement technology is also of great significance. [0003] The traditional measurement method is mainly manual measurement, that is, the measurement of size and shape and position error is carried out by measu...

AI Technical Summary

Problems solved by technology

Traditional measurement technology can no longer meet the heavy quality inspection tasks and increasingly stringent accuracy requirements

[0004] At present, there are still many deficiencies in machine vision measurement technology. In actual industrial applications, the measurement accuracy is not high enough to meet the high-precision measurement requirements, and the adaptability to the measurement environment is poor, which restricts machine vision measurement technology. Applications

Images