DM, TDI, and AOI Color Models for Automated Screen Defect Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the production process, especially in screen production, defects in products are often detected manually, which is time-consuming and prone to human error, leading to inefficiencies and inaccuracies in defect detection.
Innovation Solution
A method and device for detecting defects using multiple types of images (DM, TDI, AOI color) with defect detection models trained by the same initial model, allowing for efficient and accurate defect detection by leveraging deep learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual defect detection is used in the production process, then operational simplicity is maintained, but detection efficiency and accuracy deteriorate due to time consumption and human error
Solution Approach 1:
The patent replaces the manual mechanical inspection system with an automated deep learning-based image processing system. Multiple types of images (DM, TDI, AOI color) are automatically captured and processed by defect detection models trained on these image types, eliminating manual intervention while significantly improving detection efficiency and accuracy.
Solution Approach 2:
The patent segments the defect detection process into distinct modules for different image types (DM images, TDI images, AOI color images), each processed by specialized defect detection models. This segmentation allows parallel processing of multiple image types, improving overall detection efficiency while maintaining system organization.
2Measurement precision
If multiple types of images are processed with specialized defect detection models, then detection accuracy improves, but device complexity increases
Solution Approach 1:
The patent employs a unified deep learning framework that can process multiple types of images (DM, TDI, AOI color) through different defect detection models. The system uses a common architecture with shared components (such as the use of same initial model for training different defect detection models) while maintaining specialized processing for each image type, achieving multi-functionality without excessive complexity.
Solution Approach 2:
The patent applies specialized defect detection models tailored to specific image types (DM models for DM images, TDI models for TDI images, AOI color models for AOI color images). Each model is locally optimized for its specific image type to maximize detection accuracy, while the overall system maintains a unified structure for efficient management.
Data Source
AI summary
Provided is a method and device for detecting defect, a computer readable storage medium and an electronic device, the method including: acquiring (S310) a detection task, and acquiring various types of images corresponding to the detection task; acquiring (S320) defect detection models trained by a same initial model corresponding to the types of the images respectively; and obtaining (S330) defect detection results by performing defect detection on respective type of images using the defect detection model corresponding to the type of the images.