Screen Cover Detection via Line Segment Orientation Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current automated methods for detecting cracks in mobile devices often result in high false-positive indications due to the presence of screen covers, leading to inconsistent and inefficient evaluation processes.

Innovation Solution

The system employs machine vision to identify line segments in images of mobile devices, calculating their orientations and determining if they exceed predetermined thresholds for horizontal, vertical, or corner alignments, along with bubble detection, to accurately determine the presence of screen covers and differentiate them from genuine cracks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated methods are used to detect cracks in mobile devices, then evaluation speed and consistency are improved, but false-positive indications increase due to screen covers

Engineering Contradiction:
Improveevaluation speedVSAvoidfalse-positive rate
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The crack detection process is segmented into multiple stages: initial crack detection, screen cover detection, and conditional re-detection. The system divides the evaluation into distinct phases where screen covers are identified first through their characteristic horizontal/vertical line patterns, then crack detection is performed conditionally based on screen cover presence, reducing false positives while maintaining high evaluation speed

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes detection parameters dynamically based on screen cover detection results. When a screen cover is detected (identified by predominant horizontal or vertical line segments), the system adjusts subsequent crack detection parameters to account for the screen cover's characteristic patterns, thereby reducing false-positive indications while maintaining evaluation efficiency

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If manual inspection is used to evaluate mobile devices for cracks, then detection accuracy is improved, but evaluation time and labor requirements increase

Engineering Contradiction:
Improvecrack detection accuracyVSAvoidevaluation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary screen cover detection before conducting detailed crack detection. By first identifying the presence of screen covers through their characteristic line patterns (horizontal or vertical segments exceeding thresholds), the system prepares appropriate detection parameters in advance, enabling automated crack detection to achieve manual-level accuracy without the time cost of manual inspection

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system replaces manual visual inspection with an automated machine vision system that uses image processing algorithms to detect cracks. The automated system analyzes line segment orientations and patterns in device images, substituting human evaluators with computational methods that provide consistent, accurate results while significantly reducing evaluation time and labor requirements

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3469550B1Methods and systems for detecting screen covers on electronic devices
Publication Date: 2023.09.06 ECOATM LLC
  • EP3469550B1 patent drawingFigure 1
  • EP3469550B1 patent drawingFigure 2
  • EP3469550B1 patent drawingFigure 3

AI summary

Systems and methods for detecting the presence or absence of screen covers on electronic device screens are disclosed. In one embodiment, the method includes obtaining an image of a front side of an electronic device and automatically identifying line segments in the image. For each identified line segment, the method includes calculating the angle of the identified line segment. The method further includes determining an amount of the line segments having vertical or horizontal orientations. If the amount of identified vertical or horizontal line segments exceeds a predetermined threshold amount, then the presence of a screen cover is indicated.