Overhead Scanner Page Turn Detection via Image Difference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional overhead scanners suffer from low accuracy in detecting the start of a read operation due to false detection of movements other than the predetermined movement, leading to inaccurate detection of page turning movements.
Innovation Solution
An overhead scanner system that includes an area sensor and a control unit capable of successively obtaining images, calculating movement patterns through image difference extraction, detecting page turning movements, and determining the start of a read operation based on these patterns, while excluding false-positive detections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional overhead scanners use simple movement detection methods, then the device complexity is reduced, but the measurement precision of page turning movement detection deteriorates due to false detections
Solution Approach 1:
The detection process is segmented into multiple distinct steps: obtaining successive area images, calculating movement patterns through image difference extraction, detecting page turning movements based on calculated patterns, and determining read operation start. This segmentation allows each step to be optimized independently, improving detection precision without requiring the entire system to be overly complex.
Solution Approach 2:
The system performs preliminary actions by successively obtaining area images and calculating movement patterns before actually detecting page turning movements. The movement pattern calculation based on image difference extraction is performed in advance, creating a foundation for more accurate page turning detection and reducing false positives.
2Speed
If conventional scanners use feature point velocity vectors for movement detection, then the detection speed is improved, but the reliability of detection deteriorates due to false detection of non-predetermined movements
Solution Approach 1:
The system uses feedback by comparing successive area images and calculating movement patterns based on image differences. This continuous feedback loop allows the system to distinguish between genuine page turning movements and other movements, improving reliability while maintaining detection speed through efficient image processing.
Solution Approach 2:
The patent replaces conventional feature point velocity vector methods with image difference extraction methodology. This substitution uses area image data and movement pattern calculation instead of relying on feature point tracking, thereby improving detection reliability by reducing false detections of non-predetermined movements while maintaining acceptable detection speeds.
3Measurement precision
If high-resolution sensors are used to improve detection accuracy, then the measurement precision is improved, but the use of energy and device cost increase
Solution Approach 1:
The system applies partial action by using area sensors that capture broader regions rather than high-resolution point sensors. The movement pattern calculation based on image difference extraction processes only the necessary image data to detect page turning movements, avoiding the energy consumption of high-resolution sensors while maintaining sufficient detection precision through smart image processing.
Data Source
AI summary
An overhead scanner successively obtains a plurality of images by controlling an area sensor, calculates a movement pattern by image difference extraction by using the obtained images, detects a page turning movement on the basis of the movement pattern, and determines that a read operation be started when the page turning movement is detected.