LCD Screen Defect Detection Using Pixel Clustering and Size Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The detection of LCD screen defects, particularly linear defects, is challenging due to their proximity to the screen's brightness, leading to manual detection methods that are eye-straining and prone to missed defects, increasing the likelihood of defective products entering the market.
Innovation Solution
A method and device for automatic defect detection on LCD screens involving image acquisition, rough defect positioning, pixel clustering, and accurate defect classification based on width and length analysis to distinguish between point and linear defects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual defect detection is used, then operators can identify defects, but operator eye strain increases and vision is damaged
Solution Approach 1:
The patent replaces manual visual inspection with an automated image processing system that uses camera acquisition, threshold processing, and morphological operations to detect defects. This substitutes the mechanical human eye and brain with an automated optical and computational system, eliminating eye strain while maintaining detection capability.
Solution Approach 2:
The system performs self-service defect detection through automated algorithms that process images independently without human intervention. The threshold processing and morphological operations automatically identify and classify defects, allowing the system to serve itself rather than requiring continuous human operational input.
2Reliability
If manual defect detection is used for long periods, then defects can be detected, but missed inspection occurs due to operator fatigue
Solution Approach 1:
The patent replaces manual inspection with an automated system that continuously processes images without fatigue. The computational algorithms maintain consistent detection performance throughout operation, eliminating the decline in reliability that occurs with prolonged manual work.
Solution Approach 2:
The automated system enables continuous defect detection without interruption or decline in performance. Unlike human operators who experience fatigue over time, the automated image processing system maintains constant alertness and detection capability, ensuring continuous reliable inspection.
3Measurement precision
If manual defect detection is used, then defects can be identified, but detection precision decreases for linear defects near brightness boundaries
Solution Approach 1:
The patent applies local quality enhancement by processing different regions of the image with appropriate morphological operations. Linear defects are specifically targeted through directional morphological operations that enhance their visibility against the brightness boundary, while other regions are processed accordingly to maintain overall detection precision.
Solution Approach 2:
The system enhances defect visibility by transforming grayscale intensity information into enhanced contrast through threshold processing and morphological operations. This converts subtle brightness variations into more distinct visual patterns that are easier to detect and measure precisely.
4Ease of operation
If automated defect detection is implemented, then operator strain is reduced, but device complexity increases
Solution Approach 1:
The patent segments the defect detection process into distinct functional modules: image acquisition, threshold processing, morphological operations, and defect classification. This segmentation allows each component to be optimized independently and simplifies the overall system architecture by dividing complexity into manageable units.
Solution Approach 2:
The system achieves multi-functionality by using a single integrated image processing pipeline to perform multiple tasks: defect detection, defect classification (point vs. linear), and quality assessment. This universal approach reduces overall system complexity compared to having separate specialized systems for each function.
Data Source
AI summary
A defect detection method for an LCD screen includes acquiring a screen image of the LCD screen, performing a rough search for defects in the screen image to extract a suspected area where the defects are located, (based on the suspected area) clustering every pixel point in the suspected area to obtain clustering results, and each clustering result corresponds to a suspected defect, and (according to the clustering result) calculating a width and length of the suspected defect corresponding to the clustering result, and determining whether the suspected defect is a screen defect and which type of screen defect it belongs to based on the width and length of the suspected defect. The technical solution of the present disclosure realizes automatic detection of screen defects by rough positioning and accurate positioning of suspected defects, and the detection results are accurate and reliable.