Machine Vision and Deep Learning Based Rubber Gasket Defect Detection

Abstract

This study develops an automated optical inspection system for silicone rubber gaskets using traditional rule-based and deep learning detection techniques. The specific object of interest is a 5 mm × 10 mm × 5 mm mobile device power supply connector gasket that provides protection against foreign body inclusion and water ingression. The proposed system can detect a total of five characteristic defects introduced during the mold-based manufacture process, which range from 10-100 μm. The deep learning detection strategies in this system employ convolutional neural networks (CNN) developed using the TensorFlow open-source library. Through both high dynamic range image capture and image generation techniques, accuracies of 100% and 97% are achieved for notch and residual glue defect predictions, respectively.