Indonesian Journal of Electrical Engineering and Computer Science Vol. 19, No. 1, July 2020, pp. 188~195 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v19.i1.pp188-195  188 Journal homepage: http://ijeecs.iaescore.com Intelligent security system detects the hidden objects in the smart grid Ammar Wisam Altaher 1 , Abdullah Hasan Hussein 2 1 Al-Furat Al-Awsat Technical University, Technical Collage of Management, Iraq 2 Imam Al-kadhum University College, Iraq Article Info ABSTRACT Article history: Received Jul 1, 2019 Revised Jan 14, 2020 Accepted Feb 8, 2020 Monitoring the general public gathered in large numbers is one of the most challenging tasks faced by the law and order enforcement team. There is swiftly demand that has inbuilt sensors that can detect the concealed weapon, from a standoff distance the system can locate the weapon with very high accuracy. Objects that are obscure and invisible from human vision can be seen vividly from enhanced artificial vision systems. Image Fusion is a computer vision technique that fuses images from multiple sensors to give accurate information. Image fusion using visual and infrared images has been employed for a safe, non-invasive standoff threat detection system. The fused imagery is further processed for specific identification of weapons. The unique approach to discover concealed weapons based on DWT in conjunction with Metaheuristic algorithm Harmony Search Algorithm and SVM classification is presented. It firstly uses the traditional discrete wavelets transform along with the hybrid Hotline transform to obtain a fused imagery. Then a heuristic search algorithm is applied to search the best optimal harmony to generate the new principal components of the registered input images which is later classified using the K means support vector machines to build better classifiers for concealed weapon detection. Experimental results demonstrate the hybrid approach which shows superior performance. Keywords: Image analysis Image fusion Infrared image Object detection Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Ammar Wisam Altaher, Department of Iinformation Technology, Technical Collage of Management, Iraq. Email: dr.ammar@atu.edu.iq 1. INTRODUCTION The recent times have seen a lot of political upheavals and public unrest across the world. Safety and security of public life and public assets such as [1] airport, shopping mall, railway, bus stations have been constantly under threat by self-employed threat organizations for their vested interest. In such situations, the most challenging task of the law and order enforcement would be to perform unrestricted screening and safety surveillance system [2, 3] in all public assets with respect to human privacy and with a minimum ratio of the fail cause of related with people life. There is an argent and swiftly demand the need for intelligent surveillance and security systems that have and support inbuilt sensors which any hidden explosive or weapon from a standoff distance. The new intelligent system is a revolution in international security as it can discover future terror threats and it is of paramount importance to the law and order enforcement team who allocate significantly Investment annually to safeguard the innocent lives from new and emerging threats. The burning issue faced by the law and enforcement personnel is identifying the weapons covered with fabrics concealed under human clothing [2]. The detection system can be very necessary to prevent the real threats to the society, the public places can be monitored manually or by a specific gate to detect the dangerous materials. The objective of this work is to design and develop an automated concealed weapon detection system based on image analysis processing and machine-learning principles. The proposed future work supposed to use