Part defect detection method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a part defect detection method, device and equipment and a storage medium. The method comprises the following steps: determining a simulation part sample model; processing the simulation part sample model based on a simulation light source model, and determining a defect detection simulation training sample set; and performing model training according to the defect detection simulation training sample set, and determining a part defect detection model for detecting defects of a part entity. The embodiment of the invention provides the method and the device, the defects of the parts can be detected. According to the method, the problem of poor performance of an assembly quality detection model obtained through training due to the fact that enough and high-quality training data is difficult to obtain when part defect detection is carried out is solved, so that the high-precision training data is obtained to obtain the high-performance quality detection model in time before part defect detection is carried out, and the effect of improving the part defect detection accuracy is achieved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of computer vision, and in particular, to a method, device, equipment and storage medium for component defect detection. Background technique [0002] Computer vision technology based on deep learning has been widely used in intelligent manufacturing. At present, the training process of deep learning still requires a large amount of training data. The number and quality of training samples determine the quality of the training model. [0003] In some application scenarios, the problem of insufficient training data is particularly prominent, that is, the "small sample" problem. For example, some sites are in limited space, for example, when performing part defect detection, there are obstacles in the implementation level to capture a large amount of training data, resulting in a small amount of training data acquired. At present, in order to solve the above problems, there is a technolo...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a part defect detection method, device, equipment and storage medium to solve the problem that it is difficult to obtain sufficient and high-quality training data during part defect detection, resulting in poor performance of the part defect detection model obtained through training

Images