Ariefwan, Mohammad Rafka Mahendra (2024) Implementasi Pengenalan Wajah Untuk Sistem Presensi dengan Menggunakan Metode CNN Berbasis Android. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
20083010025.-cover.pdf Download (821kB) | Preview |
|
|
Text (BAB1)
20083010025.-bab1.pdf Download (159kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB2)
20083010025.-bab2.pdf Restricted to Registered users only until 19 January 2026. Download (600kB) |
|
|
Text (BAB3)
20083010025.-bab3.pdf Restricted to Registered users only until 19 January 2026. Download (547kB) |
|
|
Text (BAB4)
20083010025.-bab4.pdf Restricted to Registered users only until 19 January 2026. Download (6MB) |
|
|
Text (BAB5)
20083010025.-bab5.pdf Download (133kB) | Preview |
|
|
Text (Daftar Pustaka)
20083010025.-daftarpustaka.pdf Download (115kB) | Preview |
|
|
Text (Lampiran)
20083010025.-lampiran.pdf Restricted to Registered users only until 19 January 2026. Download (344kB) |
Abstract
The primary objective is to develop a face recognition system that is efficient in monitoring lecturer attendance within the Data Science Study Program at UPN "Veteran" Jawa Timur. Key considerations in this endeavor encompass maintaining data privacy and security, ensuring cost-effectiveness, and optimizing time efficiency. The research proposes a solution by integrating CNN model-based face recognition technology with Android devices. The approach involves training CNN models utilizing datasets of lecturer faces, with a comparative analysis of different architectures like ResNet, MobileNet, and InceptionV3. The literature review incorporates prior studies on face recognition and the corresponding architectural frameworks. The research methodology encompasses lecturer-face data retrieval, data preprocessing, model development, architectural comparison, performance assessment, and practical implementation. The findings, obtained through machine learning model testing across various architectures, indicate that the highest average accuracy achieved is 77%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | H Social Sciences > HG Finance > HG1709 Data processing T Technology > T Technology (General) |
||||||||||||
| Divisions: | Faculty of Computer Science | ||||||||||||
| Depositing User: | Mr Mohammad Rafka Mahendra Ariefwan | ||||||||||||
| Date Deposited: | 19 Jan 2024 10:09 | ||||||||||||
| Last Modified: | 19 Jan 2024 10:09 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/20308 |
Actions (login required)
 |
View Item |