Stain Detection in Banknotes Using Infrared Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated systems face challenges in detecting stained banknotes, particularly when the stain is the same color as the light source and banknotes can be presented in various orientations, making it difficult to distinguish using single color visible light.
Innovation Solution
A method involving the creation of a centrally-weighted image from pixel intensity values, applying thresholds to transform pixels into binary values, calculating a difference image between a binary reference image and the evaluation image, and indicating staining based on a predefined criterion, which includes capturing images using infra-red radiation to be independent of stain color and adjusting for orientation variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single color of visible light is used to image banknotes, then the imaging system is simple, but it cannot detect staining when the stain color matches the light source color
Solution Approach 1:
The patent changes the parameter of light wavelength from visible light to infra-red radiation. This parameter change allows detection of stains regardless of their color in the visible spectrum, as infra-red radiation interacts with the physical and chemical properties of the stain rather than its color, thereby resolving the contradiction between detection reliability and system complexity.
2Ease of operation
If banknotes are accepted in any orientation, then the system is user-friendly, but it becomes difficult to detect stains consistently across all orientations
Solution Approach 1:
The patent creates a universal binary reference image that serves as a standardized template for all banknote orientations. By comparing evaluation images from any orientation against this universal reference, the system maintains consistent stain detection accuracy regardless of how the banknote is inserted, thus resolving the contradiction between operational ease and measurement precision.
3Loss of information
If image processing is performed on all pixels, then complete information is retained, but processing time and computational resources increase
Solution Approach 1:
The patent extracts only the central portion of the banknote image (excluding margins and borders) to create the centrally-weighted image. This extraction removes irrelevant information while retaining the essential areas where stains are most likely to occur, thereby reducing processing time and computational resources without significant loss of detection-relevant information.
Solution Approach 2:
The patent segments the image processing into distinct stages: creating a centrally-weighted image from the central portion, converting to binary values, and then comparing with the reference image. This segmentation allows the system to process only the most relevant portions of the image in detail, reducing overall processing time while maintaining detection accuracy.
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
Enables reliable detection of stained banknotes regardless of orientation and stain color, allowing for accurate identification and removal of stained banknotes from circulation.
Implementation Method 1
The step of capturing an image of the media item may further comprise capturing a transmission image of the media item using an infra-red radiation transmitter on one side of the media item and an infra-red radiation detector on the opposite side of the media item
Data Source
Figure 1
Figure 2a~2b
Figure 2c
AI summary
A method of detecting staining on a media item is described. The method comprises: receiving an image of the media item (step 418), where the image comprises a plurality of pixels having different intensity values within a range of intensity values. Central weighting is applied to the received image to expand a central portion of the range of intensity values (step 422). A threshold is applied to each pixel in the centrally-weighted image (502) to transform each pixel to a binary value thereby creating an evaluation image (504) comprising a plurality of pixels, each having one of two possible values (step 424). A difference image (510) is created by comparing a pixel in the evaluation image (504) with a pixel in a binary reference image (206) at a corresponding spatial location (step 430), so that the difference image (510) includes (i) a stain pixel at each spatial location in which a pixel in the evaluation image (504) has a low intensity pixel and the corresponding pixel in the binary reference image (206) has a high intensity pixel, and (ii) a non-stain pixel at all other spatial locations. The media item is identified as stained (step 434) in the event that the difference image meets a staining criterion (step 432).