Sie sind auf Seite 1von 20

Watermarks Based Fake Peso Bill Detection Build

Using Image Processing

By

Jade Santos

Bachelor of Science in Computer Science

Thesis Adviser
Chapter 1

INTRODUCTION

Background of the Study

In the current time people can't imagine their life without technology. Various

technologies are helping people to live their life with more luxury. The technology sector

has changed and developed many products, one great example for this is the camera.

There are tons of things that can be done using cameras: recording, tracking,

detecting, and many more. In this research, the author introduces another way of using

camera by detecting the water marks to ensure if the money is fake or real.

Nowadays, counterfeiting of peso bill is a major issue in our country. This system

can strengthen the security to schools, companies, businesses, banks or other areas

where currency is involved. This research is most helpful for those people whose work

immerse in the cashier to prevent the fake peso bill by detecting the water mark using

android phone camera.

This system is for security purposes for those companies, school, business,

banks or other that needed in their cashiers offices where there income is coming from

the bank and by the use of image processing the camera will detect the serial number of

the peso bill to know if it is same from the databases of banks by using the android

phone camera.
This research can be helpful for those people working inside the cashier to

prevent the fake peso bill by detecting the serial number using android phone camera.

The purpose of this system is to strenghten the security for cashier offices or other

companies by the use of camera. And it will be helpful for many people needs this

system because this system is not only for those working in the cashier offices it can be

use by anyone. Let us supposed a common person withdraw in a bank and confuse if

the money is real or fake they can use this system by the use of camera by pointing the

camera in the peso bill then the camera will detect if it is fake or real.

Statement of the Problem

Specifically, the author tried to find out the answers to the following:

1.) Is this system useful for people?

2.) How can this system help people whose work immerse in currency?

3.) Can this system ease peoples doubts in their money?

Objectives of the Study

The main objective of this project is fake peso bill detection using Android

Smartphone as an application. Fake peso bill detection is a process of finding the

forgery currency. Image of the paper currency to be detected will be acquired by our

android smart phone using image processing. Specifically, the researcher aims to meet

the following objectives:


To design a camera application using android camera that can detect the

watermarks if the peso bill is real or fake.

To develop an algorithm using image processing for extracting the water mark

of the peso bill.

To evaluate the accuracy of the data that gathered of the image processing by

detecting the water mark of the peso bill.

Significance of the study

Business owners - This study will help them strenghten the security of their

profit money to avoid the fake peso bill from entering their business.

Workers and Students - This study will help them avoid the fake peso bill by

using thier android phones.

Future Researchers - This study will benefit and help the future researchers as

their guide. And also by having this study of the device and system itself, they can

easily come up with much more powerful and useful device.

Scope and Delimitations of the Study

The proposed project can determine whether the peso bill is real or fake by

detecting the water mark of it. The water mark of the peso bill can be detected through

the use of image processing of a camera which is stored in a database. The detected

water mark will know if the water mark is the same from the real peso bill. This

proposed project may not be able to detect the water mark if the money is not from our
country. This system can only detect philippine money or peso bill. If they do so the

system will not be able to distinguish if the money is real or fake.

Chapter 2

REVIEW OF RELATED LITERATURE

In this Chapter was discussed about the related literature and studies regarding

to fake peso bill, image processing, detection, serial number recognition using android

phones. It also discuss and showed the theoretical and conceptual framework.

Optical Character Recognition: (Ma, D., Lin, Q., & Zhang, T. 2000) OCR,

Optical Character Recognition, is developed to translate scanned images of

handwritten, typewritten or printed text into machine-encoded text. A lot of OCR

software have been developed to accomplish this mission. Tesseract, originally

developed as proprietary software at HwelettPackard between 1985 and 1995, now

sponsored by Google, is considered to be one of the most accurate open source OCR

engine currently available. It is capable of recognizing text in variety of languages in a

binary image format.

Camera: (Ramsiya, M. P., Reshma, N., Fazeela, V., Kuttan, N. P., Reshma, M.

V., & Akkikavu, T) Camera is used to record the image of entering currency. Here the

camera that feeds or streams its image in real time to or through a computer to
computer network. When captured by the computer, the video stream may be saved,

viewed or send on to other networks via systems such as the Internet, and email as an

attachment. Webcams are known for their low manufacturing cost and their high

flexibility, making them the lowest cost form of video-telephony. Despite the low cost,

the resolution offered at present is rather impressive, with low end web cams offering

resolution of 320*240 , medium web cams offering 640*480 resolution, and high end

web cams offering 1280*720 0r even 1920*1080 resolution. They have also become a

source a of security and privacy issues, as some built in web cams can be remotely

activated via spyware.

Edge Detection: (Pilania, E., & Arora, B.) It is the fundamental tool in image

processing, which aim at identifying points in digital image at which the image

brightness changes sharply or has discontinuities. There are many ways to perform

edge detection. . Edges are detected of the gray scale image of paper currency using

Sobel operator. It smoothes the image and calculate the gradient of the image. Edge

detection is one of the fundamental steps in image processing, image analysis, image

pattern recognition, and computer vision techniques.

RecognizeText: The attributes of this class are characters and text. It mainly

matches the characters of the LocalizeImage and classify them using the classification()

method. In order words, it recognizes only Latin Alphabet which is sent to the

UserApplication class by the method RecognizeText(), else it returns garbage data.


Image pre-processing: (Alekhya, D., Surya Prabha, G. D., & Durga Rao, G. V.

2014) The aim of image pre-processing is to suppress undesired distortions or enhance

some image features that are important for further processing or analysis.

Image Segmentation: (Alekhya, D., Surya Prabha, G. D., & Durga Rao, G. V.

2014) Image segmentation is the process of partitioning a digital image into multiple

segments (sets of pixels, also known as superpixels). 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. Image segmentation is typically used to locate

objects and boundaries (lines, curves, etc.) in images.

Image Acquisition: (Ingulkar Ashwini Suresh1, Prof.P.P.Narwade2) The first

stage of any vision system is the image acquisition stage. After the image has been

obtained, various methods of processing can be applied to the image to perform the

many different vision tasks. Performing image acquisition in image processing is always

the first step in the workflow sequence because, without an image, no processing is

possible. There are various ways to acquire image such as with the help of camera or

scanner. Acquired image should retain all the features.


Theoretical Framework

Figure 1. Theoritical Framework (Alekhya, D., Surya Prabha, G. D., & Durga Rao, G. V. 2014)
Conceptual Framework

Figure 2.

Conceptual Framework
Definition of terms

Android Studio - Used as the microcontroller of the system and this application can

create a program using the language of java.

Android phones - Used as the device to enable the application of the camera

application to read the serial number of the peso bill.

OCR (Optical Character Recognition ) - Used as the mechanical or electronic

conversion of images of typed, handwritten or printed text into machine-encoded text.

SQL Database - The storage of the data gathered by the system.

Camera Detection - Used as factors to be considered before proceeding to serial

number recognition.

Image Processing - The method used to extract the useful information coming the

image.

Edge detection - Used as identifying image which the texture and brightness changes

sharply or, more formally.


Chapter 3

METHODOLOGY

In this chapter, we showed our project design and discussed about our project

development on what kind of hardware we used. We also discussed different algorithms

that we used and how we implemented those algorithms to our system.

Project Design

Phase I: Android Phone Camera

Figure 3.1 Block Diagram of the proposed system


Phase I: Android Phone Devices

Figure 1: Android Phone Application Camera

The hardware I will be using is an android mobile operating system that is a

software stack for touchscreen mobile devices, such as smartphones and tablet

computers by this system I enable the application of the camera in my android phone by

developing the application in android studio. The camera need to be focus in the peso

bill to recognize the serial number of the peso bill.


Phase II: Camera Detection

Figure 2: Camera Detection

Figure 2: Camera Detection of phase 2. By the use of image pre-processing is

to suppress undesired distortions or enhance some image features that are important

for further processing or analysis.

Edge detection is the name for a set of mathematical methods which aim at

identifying points in a digital image at which the image brightness changes sharply or,

more formally, has discontinuities. The points at which image brightness changes

sharply are typically organized into a set of curved line segments termed edges.

Image adjusting is the image we got from scanner or digital camera is too big. So

calculations are going to be a bigger one. In order to reduce this calculation we are

reducing the size of image. Image Adjusting is done with the help of image interpolation
technique which is used for tasks such as zooming, rotating, shrinking, and for

geometric corrections.

Phase III: Serial Number Recognition

Figure 3: Serial Number Recognition

Figure 3: Serial Number Recognition of phase 3. The performance of this system

is evaluated by the rate of successful recognition. I decide to use recognition rate rather

than successful translation rate as the criterion of performance, because the recognition

rate more directly measures the successfulness of the text identification algorithm by

the use of Optical Character Recognition (OCR) which is converting images with printed

text to text format and making printed text accessible for text utils.

RecognizeText the attributes of this class are characters and text. It mainly

matches the characters of the LocalizeImage and classify them using the classification

method. In order words, it recognizes the serial number which is sent to the

UserApplication class by the method RecognizeText(), else it returns garbage data.


Phase IV: SQL Database
Project Development
Testing and Operation Procedures

% Load an image

I = imread('PesoBill.png');

% Perform OCR

results = ocr(I);

% Display one of the recognized words

word = results.Words{2}

% Location of the word in I

wordBBox = results.WordBoundingBoxes(2,:)

word =

'ZS280333*'

wordBBox =

173 75 376 61

% Show the location of the word in the original image

figure;

Iname = insertObjectAnnotation(I, 'rectangle', wordBBox, word);

imshow(Iname);
Project Evaluation
References:

[1] Alekhya, D., Surya Prabha, G. D., & Durga Rao, G. V. (2014). Fake currency
detection using image processing and other standard methods. IJRCCT, 3(1), 128-131.

[2] Da Silva Nunes, L. C., & dos Santos, P. A. M. (2004, October). An application of
stereoscopy and image processing in forensics: Recovering obliterated firearms serial
number. In 5th Iberoamerican Meeting on Optics and 8th Latin American Meeting on
Optics, Lasers, and Their Applications (pp. 208-212). International Society for Optics
and Photonics.

[3] Thakur, M., & Kaur, A. (2014). Various fake currency detection techniques.
International Journal for Technological Research in Engineering, 1(11), 1309-1313.

[4] Pilania, E., & Arora, B. Recognition of Fake Currency Based on Security Thread
Feature of Currency.

[5] Yadav, B. P., Patil, C. S., Karhe, R. R., & Patil, P. H. (2014). Indian Currency
Recognition and Verification System Using Image Processing. International Journal of
Engineering Science and Innovative Technology (IJESIT)(ISSN: 2319-5967 ISO 9001:
2008 Certified Volume 3, Issue 4.

[6] Prathap, S. (2014). Detection of fake currency using image processing. IJISET-
International Journal of Innovative Science, Engineering & Technology, 1(10).

[7] Atchaya, S., Harini, K., Kaviarasi, G., & Swathi, B. Fake Currency Detection Using
Image Processing.

[8] Alshayeji, M. H., Al-Rousan, M., & Hassoun, D. T. (2015). Detection method for
counterfeit currency based on bit-plane slicing technique. International Journal of
Multimedia and Ubiquitous Engineering, 10(11), 225-242.

[9] Draganic, A., Maric, M., Orovic, I., & Stankovic, S. (2017). Identification of image
source using serialnumber-based watermarking under Compressive Sensing conditions.
arXiv preprint arXiv:1703.00383.

[10] Parker, J. R. (2010). Algorithms for image processing and computer vision. John
Wiley & Sons.

[11] Stromme, A., Carlson, R., & Colege, S. Minimally Supervised Methods to Correct
Optical Character Recognition. Swarthmore College, Swarthmore, PA, 19081.

[12] Ma, D., Lin, Q., & Zhang, T. (2000). Mobile Camera Based Text Detection and
Translation. Department of Electrical Engg Department Stanford University.
[13] Zdadou, Fatima Ezzahra (2015) The Optical Capture Recognition.

[14] Ramsiya, M. P., Reshma, N., Fazeela, V., Kuttan, N. P., Reshma, M. V., &
Akkikavu, T. Counterfeit currency detection using Image Processing and Mobile
Recharge System.

[15] Yadav, B. P., Patil, C. S., Karhe, R. R., & Patil, P. H. (2014). An automatic
recognition of fake Indian paper currency note using MATLAB. International Journal of
Engineering Science and Innovative Technology, 3(4), 560-566.

Das könnte Ihnen auch gefallen