Illuminated Screen Crack Detection With False-Positive Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated methods for detecting cracks in illuminated electronic device screens are prone to high false-positive indications, making individualized manual inspection slow and cumbersome, and there is a need for improved methods and systems for accurate crack detection.
Innovation Solution
A method involving image subtraction of lighted and unlighted images, followed by image pyramid generation and kernel convolution to identify cracks at various angles, with secondary checks to reduce false positives, is employed to detect cracks in illuminated screens.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated methods are used to detect cracks in illuminated screens, then productivity is improved, but measurement precision deteriorates due to high false-positive rates
Solution Approach 1:
The system performs preliminary actions by capturing multiple images of the screen under different lighting conditions (illuminated and unilluminated states) before conducting crack detection. This preliminary image capture under varied conditions prepares the data needed for accurate subsequent analysis, allowing automated inspection to proceed without false positives from illuminated content.
Solution Approach 2:
The system introduces an intermediary processing step that compares images taken under different lighting conditions. By using the unilluminated image as a reference to subtract from the illuminated image, the system mediates between the two states to isolate actual crack features from screen content, thereby maintaining both automation and accuracy.
2Measurement precision
If manual inspection is performed to improve measurement precision, then crack detection accuracy is improved, but productivity deteriorates due to slow and cumbersome process
Solution Approach 1:
The system replaces the mechanical manual inspection process with an automated image processing system. Instead of human inspectors visually examining screens, the system uses automated capture of images under different lighting conditions followed by computational comparison and analysis, substituting mechanical human effort with automated optical and computational processes that achieve both speed and accuracy.
Solution Approach 2:
The system changes the lighting parameter by capturing images in both illuminated and unilluminated states. This parameter variation allows the automated system to distinguish between screen content (visible only in illuminated state) and actual cracks (visible in both states), enabling automated inspection to achieve manual-level accuracy without the speed penalty.
3Adaptability or versatility
If images are captured under illuminated conditions to maintain adaptability, then ease of operation is improved, but measurement precision deteriorates due to interference from displayed content
Solution Approach 1:
The system segments the inspection process into distinct phases: capturing an illuminated image (which shows screen content) and capturing an unilluminated image (which shows only physical defects). By separating these two types of information capture, the system can process them differently - using the illuminated image to maintain adaptability and the unilluminated image to ensure precision, then combining the results.
Solution Approach 2:
The unilluminated image serves as an intermediary reference that mediates between the illuminated screen content and the actual crack detection. By comparing the illuminated image against the unilluminated reference, the system filters out the interfering screen content while preserving information about physical cracks, thus resolving the conflict between adaptability and precision.
Data Source
AI summary
Systems and methods for detecting the cracks in illuminated electronic device screens are disclosed. In one embodiment, the method includes receiving an image of an electronic device screen and retrieving a plurality of kernels, each having values corresponding to a line region and a non-line region, with the orientation of the line region and the non-line region differing for each kernel. At least some of the kernels are applied to the image to obtain, at various locations of the image, values corresponding to the line regions and the non-line regions. Based on the values corresponding to the line regions and the non-line regions, cracks are automatically identified in the electronic device screen.