Sahte
The State Bank is the one which issue bank notes in Pakistan. State Bank, changes the design of bank notes from time to time. State bank uses several techniques to detect fake currency. Common people face many problems for the fake currency circulation and also difficult to detect fake currency, sup
2025-06-28 16:34:52 - Adil Khan
Sahte
Project Area of Specialization Artificial IntelligenceProject SummaryThe State Bank is the one which issue bank notes in Pakistan. State Bank, changes the design of bank notes from time to time. State bank uses several techniques to detect fake currency. Common people face many problems for the fake currency circulation and also difficult to detect fake currency, suppose that a common people went to a bank to deposit money in bank but only to see that some of the notes are fake, in this case he has to take the blame. As banks will not help that person. Some of the effects that fake currency has on society include a reduction in the value of real money; and inflation due to more fake currency getting circulated in the society or market which disturbs our economy and growth - an some illegal authorities an artificial increase in the money supply, a decrease in the acceptability of paper money and losses. Our aim is to help common man to recognize currency for originality. Proposed system is based on image processing and makes the process automatic and robust.
The product is a client-server application for providing the counterfeit note detection. The user interacts with the client side that is application and the server side responsible for checking using image processing techniques.
The techniques available to us are hardware based mostly and software based are available but only as desktop application. So, Sahte provides android user the application for submission of image and getting its result. The image processing is used to process and extract features from image and fed to Support Vector Machine for validation. SVM is trained on the dataset.
Project ObjectivesProject Objectives includes the following
- A software-based solution for fake currency detection.
- Provide an easy way to users to verify the currency notes.
- The software should give result within 5 seconds, so that user can get the result in a fairly fast way.
- Accuracy should be more than 90%.
Methodolog
Image Processing
Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. It is a type of signal processing in which input is an image and output may be image or characteristics/features associated with that image.
Following are some steps of Image processing:
Image Acquisition
The image of the currency that has to be checked or verified as a genuine currency is taken as an input for the system. The input image can be acquired using techniques like scanning the image or clicking a picture with the phone and then using it. In this, we will to acquire image using mobile phone.
Blur Detection
The image that is blur we cannot find edges and separate features and it is of no use. So, our first step in image processing will be blur detection, which will tell us if the image is blur or not and it can be used for further processing or not.
Image Preprocess
As the image capture from the mobile camera can have more objects than the currency note. In order to crop to note we will do edge detection and crop the image.
Edge detection is an image processing technique for finding the boundaries of objects within images. It works by detecting discontinuities in brightness. Edge detection is used for image segmentation and data extraction in areas such as image processing, computer vision, and machine vision. The purpose of detecting sharp changes in image brightness is to capture important events and changes in the properties of the world.
Detecting Currency Denomination
Currency note denomination defines the value of that currency note. As the images shown above the denomination of that note is 500pkr. Every denomination has different models generated from SVM and so it is necessary for us to check the denomination and pass it to the correct model.
Feature Extraction and Image Segmentation
We will first perform the image segmentation (obtaining the required features) and then further processing is done.
Image segmentation
In computer vision, image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as image objects). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze.
Feature extraction is a type of dimensionality reduction that efficiently represents interesting parts of an image as a compact feature vector. This approach is useful when image sizes are large and reduced feature representation is required to quickly complete tasks such as image matching and retrieval. The features are extracted and then used in the further step.
For the three selected features, we will apply the following algorithms to enhance the image.
Comparison
The features that are extracted from the previous step are used for comparing with the stored features and then the results are displayed as original or fake.
Benefits of the ProjectThe benefits of the project are following
- The software will be free of cost and will be easily available.
- The software will cater the big android market as.
- The software will use the image taken from mobile, nothing else is required.
Final Deliverable will need the following
An android device that will be used to capture picture of currency note and running client side of application. The android device should have WIFI and 8MP camera to capture image and submit it to the server.
The server side will run on PC which will accept user request and return its result. The server side PC will have at least 8gb ram and good GPU that provides good speed to user and it should be available 24/7.
Final Deliverable of the Project Software SystemCore Industry ITOther Industries Others Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Decent Work and Economic GrowthRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 58000 | |||
| Android Mobile | Equipment | 1 | 15000 | 15000 |
| Nvidia Tesla K20 | Equipment | 1 | 32500 | 32500 |
| Transcned 8GB Desktop DDR4 RAM | Equipment | 1 | 10500 | 10500 |