International Journal of Electrical and Computer Engineering (IJECE) Vol. 8, No. 3, June 2018, pp. 1903~1912 ISSN: 2088-8708, DOI: 10.11591/ijece.v8i3.pp1903-1912  1903 Journal homepage: http://iaescore.com/journals/index.php/IJECE Content-based Image Retrieval System for an Image Gallery Search Application Nicole Tham Ley Mai 1 , Syahmi Syahiran Bin Ahmad Ridzuan 2 , Zaid Bin Omar 3 1,2 Faculty of Electrical Engineering Universiti Teknologi Malaysia, Johor Bahru, Malaysia 3 Department of Electric and Computer Engineering Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru, Malaysia Article Info ABSTRACT Article history: Received Jan 27, 2018 Revised Apr 20, 2018 Accepted Apr 26, 2018 Content-based image retrieval is a process framework that applies computer vision techniques for searching and managing large image collections more efficiently. With the growth of large digital image collections triggered by rapid advances in electronic storage capacity and computing power, there is a growing need for devices and computer systems to support efficient browsing, searching, and retrieval for image collections. Hence, the aim of this project is to develop a content-based image retrieval system that can be implemented in an image gallery desktop application to allow efficient browsing through three different search modes: retrieval by image query, retrieval by facial recognition, and retrieval by text or tags. In this project, the MPEG-7-like Powered Localized Color and Edge Directivity Descriptor is used to extract the feature vectors of the image database and the facial recognition system is built around the Eigenfaces concept. A graphical user interface with the basic functionality of an image gallery application is also developed to implement the three search modes. Results show that the application is able to retrieve and display images in a collection as thumbnail previews with high retrieval accuracy and medium relevance and the computational requirements for subsequent searches were significantly reduced through the incorporation of text-based image retrieval as one of the search modes. All in all, this study introduces a simple and convenient way of offline image searches on desktop computers and provides a stepping stone to future content-based image retrieval systems built for similar purposes. Keyword: Auto-tagging Content-based image retrieval Mpeg-& powered localized descriptor Principal component analysis Text-based image retrieval Copyright © 2018 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Zaid Bin Omar, Department of Electric and Computer Engineering, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia. Email: lsntl@ccu.edu.tw 1. INTRODUCTION In recent years, rapid advances in electronic storage capacity and computing power have triggered the growth of large digital image collections following the increase of users on the internet. Over the years, we have seen exponential increases in number of digital images and video both over the net and even in our own devices as we attempt to keep more memories through photos and videos. This increased usage may be due to several factors such as education, entertainment, commercial purposes, and etc. and it is now apparent that more and more images are routinely used to convey large amounts of information. Due to the increasing difficulty in making proper use of the information contained in digital images and videos, advanced information systems are now more important than ever as they are needed to manage