LCD defect detection method based on feature pyramid convolutional neural network

Abstract

The invention relates to an LCD defect detection method based on a feature pyramid convolutional neural network. The method comprises the steps of constructing a feature pyramid convolutional neural network and constructing a detection model, detecting an LCD panel picture by using the model; defect types and positions are screened and determined through output parameters. According to the method,respective advantages of the deep residual convolutional neural network and the feature pyramid network are fully utilized. According to the invention, the low-layer high-resolution image features and the high-layer high-semantic information features are effectively fused, and the type and position of the defect are directly obtained from the LCD picture by adopting single-stage detection, so that the detection efficiency is greatly improved, and the omission ratio and the false detection rate are reduced.

Description

Technical field [0001] The invention belongs to the technical field of computer vision, target detection and recognition, and particularly relates to an LCD defect detection method based on a feature pyramid convolutional neural network. Background technique [0002] At present, the LCD panels of mobile phones, computers and other displays mainly use Thin Film Transistor Liquid Crystal Display (TFT-LCD). It has the advantages of small size, thin thickness, low energy consumption, light weight, environmental protection and no radiation, and has quickly become the main material of display panels. [0003] Due to the current level of production technology, the manufacturer cannot guarantee that the LCD produced is perfect. As long as there are defects in any part of the production process, it will bring image display defects to the LCD, such as bright spots, dark spots, bright spot areas, splash screens, geometric distortion, color aberration (Mura), etc. Therefore, the LCD defect d...

AI Technical Summary

Problems solved by technology

Therefore, the existing detection methods of this kind cannot achieve efficient and accurate defect detection results, so that the LCD panel defect detection method based on deep learning is still unable to be effectively used in the actual production line, and it has become one of the problems that the entire industry needs to solve.

Images