Mura Defect Detection in Flat Panel Master Panels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in the manufacturing of flat panel displays is the detection and classification of mura defects, which are caused by process flaws and are difficult to identify due to large datasets and noise in inspection data, requiring an efficient automated system for defect detection and quality control.
Innovation Solution
An automated method and system for detecting mura defects in master panels, involving image processing techniques such as down-sampling, filtering, and convolution with defect pattern templates, to enhance image quality, detect local defects, and select appropriate candidate patterns for defect detection, allowing for automated detection, classification, and quantification of mura defects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated defect detection systems are implemented to improve inspection efficiency, then productivity increases, but device complexity and difficulty of detecting defects increase due to large datasets and noise
Solution Approach 1:
The patent segments the complex defect detection task into multiple processing stages: data acquisition, preprocessing (noise filtering, artifact removal), defect pattern recognition, and classification. This segmentation allows each stage to handle specific aspects of the problem, making the overall system more manageable and effective despite the complexity of large datasets
Solution Approach 2:
The patent introduces intermediate processing steps including noise filtering algorithms, artifact removal techniques, and feature extraction methods that act as mediators between the raw inspection data and the final defect detection. These intermediaries simplify the data structure and reduce noise before defect patterns are identified, thereby reducing detection difficulty while maintaining high productivity
2Measurement precision
If detailed pixel-per-pixel inspection is performed to improve measurement precision, then defect detection accuracy improves, but loss of time increases due to large datasets
Solution Approach 1:
The patent performs preliminary actions by pre-processing the inspection data before detailed analysis, including noise filtering, artifact removal, and feature extraction. This preliminary processing reduces the complexity of the data structure, allowing subsequent pixel-per-pixel inspection to be performed more efficiently with less time loss while maintaining high measurement precision
Solution Approach 2:
The patent applies partial processing to different regions of the master panel based on their defect likelihood or importance. High-priority regions receive full pixel-per-pixel inspection, while other regions receive processed inspection, optimizing the balance between measurement precision and time consumption across the entire large dataset
3Ease of operation
If manual inspection and annotation are used to improve ease of operation, then ease of operation increases, but productivity decreases and labor costs increase
Solution Approach 1:
The patent implements self-service by enabling the inspection system to automatically perform defect detection, classification, and quantification without requiring manual intervention. The system uses automated algorithms to analyze inspection data, identify defect patterns, and generate results, thereby maintaining ease of operation while dramatically increasing productivity and reducing labor costs
Data Source
AI summary
A method is provided for detecting mura defects in a master panel during fabrication, the master panel containing multiple flat screen displays. The method includes preparing a combined image from image data of the master panel; enhancing the quality of the combined image, including removing artifacts from the combined image; filtering the enhanced quality combined image to detect local mura defects, the local mura defects including at least one structured pattern of defined geometric shapes; applying different candidate patterns to the filtered combined image; selecting one of the candidate patterns as a defect detection pattern, the defect detection pattern being closest to the structured pattern of defined geometric shapes of the detected local mura defects; and displaying at least a portion of the defect detection pattern on a display, together with the quality-enhanced combined image.