Optical and thermal infrared multi-stage imaging detection method and device for defects in transparent components

Abstract

The invention discloses an optical and thermal infrared multi-stage imaging detection method and device for defects in transparent components, comprising the following steps: performing optical imaging on 3C transparent components, obtaining optical images, and preliminarily determining the position and size of defects in 3C transparent components; Nitrogen heats the defect position of the 3C transparent component, performs thermal infrared imaging, and obtains a thermal infrared image; performs fusion processing on the optical image and thermal infrared image, and then recognizes the defect category of the 3C transparent component through deep learning. The device includes an optical detection module, a thermal infrared detection module, a motion control module, a data fusion module, a deep learning module, an auxiliary manipulator and a display alarm module that are connected to each other through a bus. The invention uses optical imaging and thermal infrared ultrasonic imaging to detect defective products in multiple physical quantities and in a multi-level manner, and then completes optical and infrared multi-source information fusion through a convolutional neural network, thereby improving the recognition rate of 3C transparent component defect detection.

Description

technical field [0001] The invention relates to a defect detection method of a 3C transparent component, in particular to an optical and thermal infrared multi-stage imaging detection method and device for a defect of a 3C transparent component. Background technique [0002] In my country's 3C industry, the application of transparent components continues to grow, especially with the rapid advancement of 5G technology, glass components are widely used in terminal communication products. However, due to the characteristics of transparent components in the 3C industry, the difficulty of defect detection is constantly increasing. At present, many production enterprises mainly rely on manual inspection, and the degree of automation is not high. However, the manual method relies on the experience of workers, it is difficult to unify the standard scale, and the labor intensity is very high, which affects the health of eyesight. Skilled workers have to transfer before retirement ag...

AI Technical Summary

Problems solved by technology

However, due to the characteristics of 3C transparent components: small size, many types, and inconspicuousness, if only relying on conventional visible light for identification, its detection accuracy needs to be improved

Images