A machine vision-based paddle shadow pad printing defect recognition method

Abstract

The invention discloses a machine vision-based paddle shadow pad printing defect recognition method, comprising the following steps: collecting and acquiring the image of the paddle to be detected; It is a generalized unqualified product; use the classified defect image set to train the AI ​​​​algorithm model to obtain an AI algorithm model classifier, and use this classifier to classify the generalized unqualified products; the generalized unqualified products that meet the targeted detection conditions The product is changed to a qualified product. Through the above method, the detection of different defects is treated differently, and the quality inspection process of the product is more realistically restored. At the same time, by setting different quality control errors for different types of defects, the quality control level of qualified products can be adjusted, which reflects the quality control idea in industrial production. , making machine vision defect detection flexible.

Description

technical field [0001] The invention relates to the technical field of machine vision defect detection and recognition, in particular to a machine vision-based paddle shadow pad printing defect recognition method. Background technique [0002] During the pad printing process, the paddle shadow on the propeller of the drone will have defects such as pad printing offset, pad printing with more oil, pad printing with less oil, and pad printing color difference. In order to ensure the quality of UAV products, it is necessary to detect and identify these defects. There are currently two methods of manual visual inspection and identification and machine vision automatic identification. The way of artificial vision is greatly affected by the subjective factors of personnel, and it is easy to fatigue after long-term work, which cannot guarantee the quality of inspection well. Machine vision automatic recognition is being adopted by more and more enterprises because of its advantage...

AI Technical Summary

Problems solved by technology

This way of judging the standard is too single, if the implementation is strict, it will lead to some acceptable defects, for example, the deviation within a certain deviation range will be judged as unqualified, resulting in a low product qualification rate; if the matching standard is relaxed, it will be Cause some unacceptable defects even though the features are subtle will be judged as qualified products

Images