Multi-feed Detection Using Image Shape and Ultrasonic Overlap
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medium conveying apparatuses often incorrectly detect multi-feeds when a medium with an adhered object, such as a photograph, is scanned, leading to impaired user convenience as users must manually disable multi-feed detection, and existing methods struggle to accurately differentiate between adhered objects and overlapping media.
Innovation Solution
A medium conveying apparatus that generates an input image of the conveyed medium, detects overlaps using ultrasonic sensors, and determines multi-feeds by analyzing the rectangular shape of the object area within the image, executing abnormal processing when a multi-feed is detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-feed detection function is enabled, then multi-feed accuracy is improved, but false detection occurs when photograph is adhered to medium
Solution Approach 1:
The detection process is segmented into multiple independent analysis stages: overlap detection using ultrasonic sensors, object area detection from images, rectangular shape verification, and multi-feed determination. Each stage processes specific features separately before综合 conclusion, allowing the system to distinguish between photograph adhesion (rectangular shape maintained) and actual multi-feed (shape distortion occurs).
Solution Approach 2:
The patent introduces an intermediary verification mechanism using image processing and shape analysis between the ultrasonic overlap detection and the final multi-feed determination. This intermediary stage analyzes whether the detected overlap corresponds to a rectangular object area, serving as a mediator to filter false detections caused by adhered photographs while maintaining detection of actual multi-feeds.
2Reliability
If multi-feed detection is manually disabled, then false detection is avoided, but user convenience deteriorates
Solution Approach 1:
The system performs self-service by automatically distinguishing between photograph adhesion and actual multi-feed conditions through integrated sensor data and image processing. The apparatus autonomously determines whether detected overlaps represent genuine multi-feed errors or acceptable photograph adhesion scenarios, eliminating the need for manual user intervention or setting adjustments while maintaining high detection reliability.
3Measurement precision
If shape analysis is added to multi-feed detection, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The system achieves multi-functionality by utilizing the existing imaging device for dual purposes: primary scanning function and secondary shape analysis for multi-feed detection. The same imaging hardware and processing pipeline are leveraged to extract both image content for scanning and geometric features for overlap verification, eliminating the need for separate dedicated shape detection hardware and reducing overall system complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately differentiates between adhered objects and overlapping media, reducing false multi-feed detections and enhancing user convenience by automatically handling multi-feeds without requiring manual user intervention.
Implementation Method 1
a shape of an outer periphery of a paper is changed on a boundary of an overlap detection portion of a medium based on vertical and horizontal sides of the overlap detection portion detected by an ultrasonic sensor
Data Source
AI summary
A medium conveying apparatus includes a conveying roller to convey a rectangular medium, and a processor to generate an input image acquired by imaging the conveyed medium, detect an overlap of the conveyed medium, detect an object area from the input image, determine whether an outer shape of the object area is rectangular, determine whether a multi-feed of the medium has occurred based on whether the overlap of the medium has been detected and whether the outer shape of the object area is rectangular, and execute an abnormality processing when it is determined that the multi-feed of the medium has occurred.