<![CDATA[The attendance system implemented at PT Sinergi Karya Mandiri previously depended on a paid third-party platform that still presented several weaknesses in validation accuracy. The platform only allowed manual photo uploads, creating opportunities for attendance manipulation and making employee location verification difficult to ensure. This study was conducted to design and implement an attendance system based on facial recognition technology using OpenCV in order to improve the reliability, validity, and transparency of attendance records. The proposed solution was developed as an integrated system consisting of a mobile application for employees to perform attendance through face verification and GPS-based location capture, as well as a web-based application that enables the HRD division to monitor attendance activities and generate reports in real time. System development adopted the Rapid Application Development (RAD) approach, which covers the stages of Requirements Planning, User Design, Construction, and Cutover. The implementation results indicate that the system was able to apply facial recognition using the Local Binary Pattern Histogram (LBPH) method, with the recognition process executed locally on the mobile device. This mechanism supports offline functionality while also providing faster response times. Based on black box testing, all major features operated properly and produced valid results, including HRD login, employee OTP verification, facial-recognition-based attendance, employee data management, attendance location mapping, and offline synchronization reporting. Overall, the developed system reduced dependence on external paid services, minimized fraud potential, and improved operational efficiency in attendance management.]]>
Copyrights © 2026
