Machine vision based rotary workpiece detection method

Abstract

The invention discloses a machine vision based rotary workpiece detection method. The method comprises the following steps that 1, according to the required detection precision, an industrial camera of the proper resolution ratio and a matched lens are selected, a lighting mode is selected according to the required detection technology index, and a corresponding light source is selected; 2, imagescollected by the industrial camera is subjected to distortion correction processing, a filter is adopted, the images are preprocessed, and the influence of noise on edge feature extraction is eliminated; 3, the images obtained after noise elimination is subjected to threshold segmentation, and the segmented images are subjected to workpiece edge extraction; after workpiece edge extraction, circles and straight lines of workpieces are fitted, and after fitting is completed, a corresponding calibration mode is selected for measuring corresponding technological indexes on a rotary workpiece. Themachine vision based rotary workpiece detection method is high in detection precision and wide in application range.

Description

technical field [0001] The invention relates to a detection method, in particular to a detection method of a revolving body workpiece based on machine vision. Background technique [0002] With the rapid development of science and technology, the manufacturing industry has also been greatly improved. Rotary parts play an important role in the manufacturing industry and are widely used in various fields such as ships, aviation, heavy machinery and military defense. The manufacturing accuracy of the profile of rotary parts has a great impact on their use function and assembly performance. At the same time, the production of rotary parts has the characteristics of variable batch and complex profile, which poses a challenge to the corresponding detection methods. At present, the detection methods of most rotary workpieces in China are mostly carried out by means of dial indicators, micrometers, and vernier calipers. These non-automatic measurement technologies need to rely on ...

AI Technical Summary

Problems solved by technology

The characteristic of the interpolation method is that the calculation amount is smaller than other methods, and the calculation speed is relatively fast, but the anti-noise performance is relatively poor, and the accuracy depends to a certain extent on the pixel-level positioning accuracy, which is suitable for step-type edges.

Images