Mobile application: coin identification using machine learning / Dania Qistina Mohd Nazly

Mohd Nazly, Dania Qistina (2021) Mobile application: coin identification using machine learning / Dania Qistina Mohd Nazly. Degree thesis, Universiti Teknologi MARA, Perak.


Most of the human work has been replaced by computers in recent years. With the rise of mobile technology and Internet access, recent developments in machine learning have designed many algorithms to solve diverse human problems. The prevailing transfer learning method in recent years enables researchers and engineers to conduct experiments within limited computing and time constraints. Due to a lack of exposure in image processing and the numerous designs of Malaysia coins, mobile coin identification technology is still not widely employed in Malaysia. Moreover, the procedure of classifying coins of various values is time-consuming since the number of coins in Malaysia is a lot. It is necessary to develop a system that is capable of accurately recognizing and identifying coins in a short amount of time.Therefore, this paper outlines the steps involved in creating a mobile application for Coin Identification using Machine Learning. Besides that, it introduces the many designs of Malaysian coins. The three machine learning types and classification techniques such as Support Vector Machine, K-Nearest Neighbors, Neural Network, and Naive-Bayes Classifier are defined and studied. In Literature review, the features from the already existing coin identification mobile application are compared by their advantages and limitations. The coin dataset will be trained and tested using the chosen technique. In methodology, the design and application architecture take place to determine the optimal model to deploy it in the mobile application. The official design and implementation of the application will also be stated to state the working progress for the final year project. This includes the limitations of the mobile application that were not able to be fulfilled and future improvements that could be added in the near future.


Item Type: Thesis (Degree)
Email / ID Num.
Mohd Nazly, Dania Qistina
Email / ID Num.
Thesis advisor
Isawasan, Pradeep
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Mobile computing
Divisions: Universiti Teknologi MARA, Perak > Tapah Campus > Faculty of Computer and Mathematical Sciences
Programme: Bachelor of Computer Science (Hons.) Computer Science
Keywords: Mobile application; Coin Identification; Machine Learning; Support Vector Machine; K-Nearest Neighbors; Neural Network; Naive-Bayes Classifier
Date: March 2021
Edit Item
Edit Item


[thumbnail of 59253.pdf] Text

Download (113kB)

Digital Copy

Digital (fulltext) is available at:

Physical Copy

Physical status and holdings:
Item Status:

ID Number




Statistic details