Please use this identifier to cite or link to this item:
Title: Detecting Counterfeit Currency using Swarm Intelligence
Authors: دنيا توفيق حسون 
Supervisor: د.محمد الشايجي
Degree Awarded: Degree in: Computer Engineering
Keywords: Detecting Counterfeit Currency, Swarm Intelligence
Issue Date: 2019
Publisher:  Kuwait university - college of graduate studies
Abstract: Throughout history, currency issuers have always faced a common economical threat: counterfeiting. Nowadays, no state is immune from the circulation of counterfeiting its currency notes. Counterfeiters are becoming more difficult to track down due to their rapid adoption and adaptation to advancements in technology that is increasing each day at higher rates. Many researchers have concluded that counterfeiting occurs mostly to notes of higher denominations and that image processing is usually the initial step in detecting counterfeit currency notes. While reviewing previous studies, a trend was observed in detecting counterfeits; image acquisition, pre-processing and classifications, and a result is produced as output. Currency notes are authenticated on the basis of different security features in each currency. To determine the authenticity of a banknote, a comparison is made between the suspect image and a genuine sample image. It is crucial to explore methods of counterfeit currency detection that are efficient in terms of accuracy, reliability, and cost. The objective of this study is to experiment with the use of swarm intelligence in optimizing image processing phases such as feature selection and image segmentation, in recognizing and detecting counterfeit Kuwaiti currency notes. Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) algorithms are well known to be the most successful algorithms in the field of swarm intelligence in solving optimization problems, hence will be employed to image processing operations to achieve the best results. Applying ACO as an edge detector to images produced much clearer and accurate edges than PSO, even though it slightly consumed more processing time than PSO. Furthermore, both swarm intelligent algorithms showed clearer edges and less false edges than using traditional edge detection algorithms. Counterfeit currency notes were also detected using different techniques of image processing and various quality metrics were studied and compared to genuine currency notes.
Appears in Programs:0612 Computer Engineering

Files in This Item:
File Description SizeFormat 
Detecting Counterfeit Currency using Swarm Intelligence-Final Copy.pdf2,72 MBAdobe PDFView/Open    Request a copy
Show full item record

Page view(s)

Last Week
Last month
checked on Nov 22, 2020


checked on Nov 22, 2020

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.