Perancangan aplikasi absensi karyawan dengan menggunakan face recognition metode Local Binary Pattern Histogram (LBPH)

Alessandro, Alessandro (2024) Perancangan aplikasi absensi karyawan dengan menggunakan face recognition metode Local Binary Pattern Histogram (LBPH). Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (507kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (694kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) | Preview
	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (5MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (5MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (383kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (5MB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)

Abstract

Salah satu aspek penting dalam manajemen sumber daya manusia adalah pengelolaan absensi karyawan. Tradisionalnya, absensi karyawan dilakukan melalui metode manual seperti penandatanganan daftar hadir atau penggunaan kartu identitas. Namun, metode manual ini seringkali rentan terhadap kesalahan dan kecurangan. Oleh karena itu, diperlukan inovasi dalam sistem absensi karyawan. Penelitian ini mengusulkan perancangan aplikasi absensi karyawan berbasis pengenalan wajah dengan menggunakan metode Local Binary Pattern Histogram (LBPH). Metodologi pengembangan sistem yang digunakan pada penelitian ini adalah Waterfall Model. Metode pengujian sistem dilakukan dengan cara menguji fungsionalitas aplikasi dalam mengenali wajah karyawan terhadap 10 orang karyawan ketika melakukan absensi untuk menguji akurasi dari aplikasi yang diusulkan pada penelitian ini. Hasil penelitian menunjukkan bahwa aplikasi ini mampu mencatat kehadiran karyawan secara real-time dengan tingkat akurasi 90%, mengurangi potensi kesalahan manusia dan penipuan. Hasil temuan juga menunjukkan bahwa meskipun algoritma LBPH efektif dalam mengenali wajah dalam berbagai situasi, namun diperlukan latihan dengan data beragam dan penggunaan kontrol tambahan untuk memastikan akurasi dan keamanan, terutama dalam kondisi seperti penggunaan masker atau pencahayaan ekstrem. Dengan pendekatan ini, algoritma LBPH dapat digunakan secara efektif dalam aplikasi absensi karyawan. / One important aspect of human resource management is employee attendance management. Traditionally, employee attendance has been conducted using manual methods such as signing attendance registers or using identification cards. However, these manual methods are often susceptible to errors and fraud. Therefore, innovation in employee attendance systems is required. This research proposes the design of an employee attendance application based on facial recognition using the Local Binary Pattern Histogram (LBPH) method. The system development methodology utilized in this research is the Waterfall Model. The system testing method involves testing the application's functionality in recognizing the faces of 10 employees during attendance to evaluate the accuracy of the proposed application in this research. The research results indicate that this application is capable of recording employee attendance in real-time with an accuracy rate of 90%, reducing the potential for human errors and fraud. The findings also suggest that while the LBPH algorithm is effective in recognizing faces in various situations, it requires training with diverse data and the use of additional controls to ensure accuracy and security, especially in conditions such as the use of masks or extreme lighting. With this approach, the LBPH algorithm can be effectively used in employee attendance applications.

Actions (login required)

View Item