Touchless Banknote Counting via Anisotropic Diffusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing touchless counting methods for stacked substrates, such as banknotes, are not sufficiently accurate and robust, particularly due to issues like contrast destruction from security threads, printing inks, and paper fibers, leading to counting errors and inefficiencies compared to mechanical rotating counting discs.
Innovation Solution
A touchless counting system utilizing an optical sensor system, like a CMOS array or line-scan camera, acquires sample images of banknote stacks, processes them using anisotropic diffusion techniques with wavelet-based noise removal to preserve edge information, and separates banknote edges effectively, enabling accurate counting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of stationary object
If touchless counting methods are used to avoid mechanical wear, then device durability is improved, but counting accuracy deteriorates due to contrast destruction from security threads and printing inks
Solution Approach 1:
The patent segments the image processing into multiple stages: initial image acquisition, anisotropic diffusion filtering to enhance edges while removing noise from security threads and inks, and subsequent edge detection. This segmentation allows the system to maintain touchless operation while improving counting accuracy by systematically addressing different image quality issues at different processing stages.
Solution Approach 2:
The patent introduces anisotropic diffusion filtering as an intermediary processing step between image acquisition and edge detection. This intermediary process acts as a mediator that selectively enhances edge information while suppressing harmful contrast destruction from security threads and printing inks, thereby resolving the contradiction between touchless operation and counting accuracy.
2Measurement precision
If mechanical rotating counting discs are used to achieve accurate counting, then counting accuracy is improved, but processing speed deteriorates due to mechanical limitations
Solution Approach 1:
The patent replaces the mechanical rotating counting disc system with a touchless optical imaging and image processing system. This substitution eliminates mechanical limitations that constrained processing speed while maintaining counting accuracy through advanced digital image processing techniques, specifically anisotropic diffusion filtering followed by edge detection algorithms.
Solution Approach 2:
The patent employs dynamic image processing parameters and adaptive filtering techniques that can adjust to different banknote characteristics. The anisotropic diffusion process dynamically adjusts to preserve important edge information while removing noise, enabling the system to maintain high processing speeds across varying input conditions without sacrificing accuracy.
3Productivity
If simple image processing is used to reduce computational load, then processing speed is improved, but edge separation quality deteriorates due to noise from security threads and paper fibers
Solution Approach 1:
The patent changes the parameter space by applying anisotropic diffusion filtering with specific mathematical parameters that optimize the balance between noise removal and edge preservation. By carefully selecting and adjusting diffusion parameters, the system achieves high-quality edge separation that can be processed efficiently, resolving the contradiction between processing speed and edge separation quality.
Solution Approach 2:
The patent applies local quality enhancement through anisotropic diffusion filtering that treats different regions of the image differently. The filtering process selectively enhances edge regions while applying stronger noise suppression in homogeneous areas, thereby improving edge separation quality without uniformly increasing computational load across the entire image.
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 achieves reliable and efficient counting of banknotes, reducing processing time by a factor of 3 to 5 compared to mechanical discs, with minimal errors, and is suitable for real-time implementation in banknote production systems.
Implementation Method 1
an optical sensor system, like a CMOS array or line-scan camera, acquires sample images of banknote stacks
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There is described a method for touchless counting of substantially planar substrates, especially banknotes, which are stacked in the form of stacks of substrates, said method comprising the following steps: taking at least one sample image of a portion of a side of a stack of substrates, which sample image contains contrast information representing substrate edges that extend along substantially a first direction in the sample image; processing the contrast information representing the substrate edges within the sample image (10), which processing includes subjecting at least one area of interest (20) within the sample image (10) to anisotropic diffusion to produce a processed image containing a substantially coherent set of continuous lines representing the substrate edges; and counting the number of substrate edges in said processed image.