Pratama, Daffa Risky (2026) Perancangan Aplikasi Pengenalan Wajah Untuk Pendataan Kehadiran Pada Video Meeting Menggunakan CNN. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
19081010052.-cover.pdf Download (994kB) |
|
Text (Bab 1)
19081010052.-bab1.pdf Download (203kB) |
|
Text (Bab 2)
19081010052.-bab2.pdf Restricted to Repository staff only until 12 March 2028. Download (192kB) |
|
Text (Bab 3)
19081010052.-bab3.pdf Restricted to Repository staff only until 12 March 2028. Download (724kB) |
|
Text (Bab 4)
19081010052.-bab4.pdf Restricted to Repository staff only until 12 March 2028. Download (899kB) |
|
Text (Bab 5)
19081010052.-bab5.pdf Download (194kB) |
|
Text (Daftar Pustaka)
19081010052.-daftapustaka.pdf Download (0B) |
|
Text (Lampiran)
19081010052.-lampiran.pdf Restricted to Repository staff only Download (318kB) |
Abstract
The process of recording attendance in online meetings or video meetings involving many participants is often time-consuming and carries a risk of error if done manually. This study aims to design and build an automatic face recognition application to simplify the attendance data collection process by utilizing the Convolutional Neural Network (CNN) algorithm. The system development method used is the Incremental Model which consists of four development stages. Technically, this application uses the Haar Cascade algorithm to detect the presence of faces in video meeting screenshots and the FaceNet architecture for the face feature extraction process. Registered participant face data is stored in a JSON format-based database to then be matched with the detected faces. System testing was conducted using screenshots from a video meeting platform containing a total of 45 participant faces in various conditions. The results showed that the system is able to recognize faces with a very high level of reliability at the identification stage. Based on the evaluation results using a confusion matrix, this application produced a precision value of 100 percent, recall of 80 percent, accuracy of 80 percent, and an F1-score of 88.8 percent. In addition, consistency testing using Cohen’s Kappa yielded a value of κ = 0.93, indicating an almost perfect agreement between test configurations. The main limitations observed were detection failures on non-frontal faces and low image resolution during the screenshot process; however, the system successfully maintains attendance data integrity with no identity misidentification.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76 Computer software Q Science > QA Mathematics > QA76.6 Computer Programming |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Daffa Risky Pratama | ||||||||||||
| Date Deposited: | 13 Mar 2026 01:59 | ||||||||||||
| Last Modified: | 13 Mar 2026 02:37 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/50336 |
Actions (login required)
 |
View Item |