Neural Network Double-Feed Detection in Scanners
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting double-feed papers in photo scanners and multifunction printers rely on additional hardware, such as ultrasonic devices, which increase manufacturing costs.
Innovation Solution
A software-based solution using a neural network controller and image processing to detect noise patterns caused by back-illuminating pages, distinguishing between single sheets and sheet stacks by analyzing light intensity and overlapping paragraph patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ultrasonic transmitter and receiver are used to detect double-feed papers, then detection capability is improved, but manufacturing cost increases
Solution Approach 1:
The patent replaces the mechanical ultrasonic detection system with an optical detection system using existing light sources and image capture devices. The light source illuminates the paper and the image capture device captures images, with double-feed detection achieved through software analysis of image properties rather than mechanical ultrasonic sensors.
Solution Approach 2:
The patent makes the existing light source and image capture device serve dual functions: their primary function for scanning/documents imaging and an additional function for double-feed detection. This eliminates the need for dedicated ultrasonic detection hardware while maintaining detection capability.
2Measurement precision
If additional hardware is incorporated for double-feed detection, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent substitutes hardware-based ultrasonic detection with software-based image analysis. The neural network controller analyzes image properties captured by existing devices to detect double-feeds, replacing complex mechanical detection hardware with computational algorithms.
Solution Approach 2:
The patent introduces image processing algorithms and neural network controllers as intermediaries between the light source/image capture device and the detection function. These software components process image data to identify double-feed conditions without requiring additional physical sensors.
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
This approach effectively detects double-feed papers without the need for additional hardware, reducing costs and improving detection accuracy by leveraging existing hardware in scanning devices.
Implementation Method 1
back-illuminating the at least one page using a light source
Data Source
AI summary
Methods and system are disclosed for a double-feed detector with neural network classifier. These includes accepting pages of a print-based media substrate into a scanning device with a paper feed device, back-illuminating the pages using a light source, capturing a page image of back-illuminated pages using an image capture device, detecting noise patterns exhibited by the page image using an image processor, classifying detected noise patterns using a noise pattern classifier, and determining, using classified detected noise patterns and a neural network controller for a neural network model, whether the at least one page is a sheet stack (at least two pages stacked together and passing through the paper feed device concurrently) based on the classified detected noise patterns. On condition a sheet stack is detected, a sheet stack detected signal triggers taking an action.