A more reliable defect detection and performance improvement method for panel inspection based on artificial intelligence

Abstract

This paper presents a practical approach to automatic inspection of display panels based on deep neural networks. The approach accurately detects appearance defects on display panels in various sizes and shapes within a short computation time. We propose a novel reliable detection network using the multi-channel parameter reduction method, which preserves high-resolution features of defects at sub-sampling steps of convolutional operations. Our proposed network consists of two sub-networks with different functions: pixel-wise segmentation of defect regions and distinction of real defects from fake defects. Compared with conventional deep learning networks, the proposed network achieved a more accurate detection rate, i.e. an F1-score of 81%, for real defect images acquired from an actual display manufacturing process. In addition, we propose a conditionally paired generative network that generates synthetic images of scarce defects under four different lighting conditions. The proposed networks improved the detection accuracy and can be applied to automatic inspection processes in display manufacturing factories in place of human inspection.

Surface defect detection and classification of Si3N4 turbine blades based on convolutional neural network and YOLOv5

“…It is of vital significance to study and design a detection and classification method for surface defects of Si 3 N 4 turbine blades. 15,16 The new method plays an increasingly important part in improving the stability of product quality, 17 reducing labor intensity of workers, 18,19 and improving the level of industry automation.…”

Precise Inspection of Geometric Parameters for Polyvinyl Chloride Pipe Section Based on Computer Vision

“…The system, consisting of a mobile manipulator, a fringe projection scanner, and a stereo vision system, enables accurate noncontact three-dimensional (3D) measurements of large-scale complex components. Jeong et al [28] introduced a conditionally paired generative network to generate synthetic images of scarce defects under four different lighting conditions, and significantly improved the accuracy of detecting such defects.…”