Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Applied Sciences and Smart Technologies
Akinwunmi, Akinwale
Unknown Affiliation
Computer Science & IT Energy Engineering Industrial & Manufacturing Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
A Deep Learning Model for Identical National Flag Recognition in Selected African Countries Aworinde, Halleluyah Oluwatobi; Oladimeji, Oladosu; Adebayo, Segun; Akinwunmi, Akinwale; Sakpere, Aderonke Busayo; Oladimeji, Olayanju
International Journal of Applied Sciences and Smart Technologies Volume 05, Issue 02, December 2023
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v5i2.6452

Abstract

The national flags are among the symbolic representations of a country. They make us understand the country of interest in a particular issue. Therefore, they are commonly used in both private and government organizations. It has been discovered in recent times that the younger generation mostly and idly and spend its time online; hence, knowing little about national flags. Additionally, some national flags (particularly in West Africa) are identical in nature. The likeness is in terms of layout, colours, shapes and objects on the national flags. Hence, there is a need to have a model for flag recognition. In this paper, national flag images of some West African countries were gathered to form a dataset. After this, the images were preprocessed by cropping out the irrelevant parts of the images. VGG-16 was used to extract necessary features and to develop the deep learning model. This contrasted with the existing handcrafted feature extraction and traditional machine learning techniques used on this subject matter. It was observed from this study that the proposed approach performed excellently well in predicting national flags; with an Accuracy of 98.20%, and an F1 score of 98.16%. In the future, it would be interesting to incorporate the national flag recognition into Human-Computer Interaction System. For instance, it could be used as flag recognition in some mobile and web applications for individuals with colour blindness. This research work presents a robust model because of nature of the dataset used in this work compared to previous works.
Co-Authors Adebayo, Segun Aworinde, Halleluyah Oluwatobi Oladimeji, Oladosu Oladimeji, Olayanju Sakpere, Aderonke Busayo