| abstract |
The invention discloses an optical and thermal infrared multi-level imaging detection method and device for defects of transparent components, comprising the following steps: performing optical imaging on a 3C transparent component, obtaining the optical image, and preliminarily determining the defect position and size of the 3C transparent component; Nitrogen heats the defect positions of 3C transparent components, performs thermal infrared imaging, and obtains thermal infrared images; the optical images and thermal infrared images are fused, and then the defect types of 3C transparent components are recognized 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, which are communicated and connected to each other through a bus. The invention uses optical imaging and thermal infrared ultrasonic imaging to detect defective products in a multi-physical quantity and multi-level manner, and then completes optical and infrared multi-source information fusion through a convolutional neural network, thereby improving the identification rate of 3C transparent component defect detection. |