Digital Holographic Imaging for Optical Inspection in Learning-based Pattern Classification

摘要

High demand of optical inspection is increased to guarantee manufacture and product quality in industries. To overcomelimitations of the manual defect inspection, machine vision inspection is needed to efficiently and accurately screen theundesired defects on various products. Recently, the transparent substrate is becoming widely used for manufacturingoptics and electronics products. For high-grade transparent substrates, development of machine vision inspection hasincreased its importance for inspecting defects after production. To perform machine vision inspection for the transparentsubstrate, the exposure procedure and analysis of the capturing image are critical challenges due to its properties ofreflection and transparency. However, conventional machine vision systems are performed for optical inspection based ontwo-dimensional (2D) intensity images from the camera-based photography without phase and depth information, and maydecrease inspection accuracy as well as defect classification. Conversely, instead of the 2D intensity image by camerabasedphotography with complicated algorithms and time-consuming computation, digital holography is a novel threedimensional(3D) imaging technique to rapidly access the whole wavefront information of the target sample for opticalinspection and complex defect analysis. In this study, we propose digital holographic imaging of transparent target samplefor optical inspection in learning-based pattern classification, which a novel complex defect inspection model is presentedfor multiple defects identification of the transparent substrate based on 3D diffraction characteristics and machine learningalgorithm. Both theoretical and experimental results will be presented and analyzed to verify the effective inspection andhigh accuracy.