Citation
Zulkeefli, Siti Nur Izzati and Hashim, Noramiza (2022) Comparison of CNN-based Algorithms for Halal Logo Recognition. Journal of System and Management Sciences, 12 (5). pp. 155-168. ISSN 1816-6075, 1818-0523
Text
9.pdf Restricted to Repository staff only Download (401kB) |
Abstract
The market for halal products has been continuously growing from day to day. Along with this, the demand for halal product verification has grown. As a certification symbol, a unique halal logo can be presented on the products, and the logos are uniquely designed by each halal certification body. However, there are instances where an irresponsible party creates a fake halal logo and displays it on their product, deceiving Muslim consumers. In Malaysia, the Department of Islamic Development (JAKIM) has introduced a standard halal logo for locally manufactured products. It currently recognizes other halal logos from foreign certification bodies around the world for products imported into Malaysia. Our work proposes the use of deep learning methods to identify the various halal logos from different countries. Existing methods and algorithms are used to identify and recognize halal logos. Three deep learning methods, notably YOLOv5, Back Propagation Neural Network and MobileNetV2-SSD are compared, and it is shown that the Back Propagation Neural Network outperforms the other two methods with F1-score of 0.949. This method is then implemented on a mobile application that can be used to capture a halal logo from a product followed by recognizing the logo and its country of origin.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | logo recognition, Halal logo, backpropagation neural network, yolov5, SSD, deep learning |
Subjects: | Q Science > Q Science (General) > Q300-390 Cybernetics Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science |
Divisions: | Faculty of Computing and Informatics (FCI) |
Depositing User: | Ms Nurul Iqtiani Ahmad |
Date Deposited: | 01 Dec 2022 03:33 |
Last Modified: | 01 Dec 2022 03:35 |
URII: | http://shdl.mmu.edu.my/id/eprint/10876 |
Downloads
Downloads per month over past year
Edit (login required) |