Machine vision system testing method and system and storage medium

Abstract

The invention discloses a machine vision system testing method and system and a storage medium, which are used for testing the robustness of a machine vision system. The method comprises the following steps: collecting a target image of which the quality meets a preset condition; generating a plurality of degraded images corresponding to the target image; selecting a degraded image sample set meeting a specific scoring standard from the plurality of degraded images; inputting the degraded image sample set into a machine vision system to be tested; obtaining a first recognition result of each image in the degraded image sample set; and determining a test result of the machine vision system according to a comparison result of the first recognition result and the second recognition result. By adopting the scheme provided by the invention, the robustness of the machine vision system is tested; and secondly, a plurality of degraded images corresponding to the target image are generated in a degradation mode, so that the sample size input to a machine vision system is increased, and data augmentation is realized.

Description

Technical field [0001] The present application relates to the field of image recognition, and in particular, to a machine visual system test method, system, and storage medium. Background technique [0002] The machine vision system is a system that uses the machine instead of human eye to perform various measurements and judgments. It is an important branch of computer disciplines. The machine vision system has a wide range of applications in modern production and life. Machine vision equipment can be applied to high-volume production scenarios in the pipeline. It is also possible to identify if the workpiece on the pipeline is qualified; the machine vision equipment can also be applied to the equipment for security inspection in the subway, airport, and monitoring the passengers carrying dangerous goods; machine vision The equipment can also be applied to road traffic monitoring scenarios, whether there is violations of violations of road vehicles. It can be seen that machine v...

AI Technical Summary

Problems solved by technology

[0003] If the quality of the recognized image is good, most machine vision systems can give an accurate judgment. However, in the actual production process, there are many interference factors, such as the camera lens is polluted by oil and dust, and the ambient light changes day and night resulting in ambient brightness. Insufficient or high, out-of-focus situations caused by camera movement or subject movement, camera overheating or aging, etc.

These problems will lead to quality problems such as blurring, noise, and grayscale / contrast changes in the images captured by the camera. After the quality of the captured images is reduced, some machine vision systems cannot obtain accurate judgment results, and some machine vision systems can still Get accurate judgment results

Images