Rancang Bangun Aplikasi OMR untuk Pemeriksaan LJK secara Realtime Menggunakan DexiNed dan Active Contour

Prastyo, Kus Dwi (2026) Rancang Bangun Aplikasi OMR untuk Pemeriksaan LJK secara Realtime Menggunakan DexiNed dan Active Contour. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010091-cover.pdf Download (3MB)
	Text (Bab 1) 21081010091-bab1.pdf Download (194kB)
	Text (Bab 2) 21081010091-bab2.pdf Restricted to Repository staff only until 19 January 2028. Download (556kB)
	Text (Bab 3) 21081010091-bab3.pdf Restricted to Repository staff only until 19 January 2028. Download (3MB)
	Text (Bab 4) 21081010091-bab4.pdf Restricted to Repository staff only until 19 January 2028. Download (4MB)
	Text (Bab 5) 21081010091-bab5.pdf Download (185kB)
	Text (Daftar pustaka) 21081010091-daftarpustaka.pdf Download (192kB)
	Text (Lampiran) 21081010091-lampiran.pdf Restricted to Repository staff only Download (322kB)

Abstract

Digital image processing is a field of computer science that focuses on the analysis and interpretation of digital images to obtain meaningful information. One of its applications is Optical Mark Recognition (OMR), a technology used to detect marks on documents. In the education sector, OMR is commonly utilized for grading computer answer sheet. However, conventional OMR systems typically rely on specialized scanners that are expensive and lack flexibility. Although Computer-Based Test (CBT) systems offer automated grading, their implementation heavily depends on the availability of technological infrastructure such as computers, internet connectivity, and stable power supply. Based on these issues, this study aims to develop a web-based OMR application capable of performing realtime LJK evaluation using digital image processing techniques. The system is designed using OpenCV.js and TensorFlow.js, implementing Dense Extreme Inception Network for Edge Detection (DexiNed) for edge detection and Active Contour for answer area segmentation. These methods are combined to enable the system to adapt to variations in lighting conditions, shading thickness, and scanning positions. The testing results show that the developed system can automatically detect and evaluate answer sheets with high accuracy (100%) under various conditions. The system performs optimally under normal lighting and fully shaded marks, with slight accuracy reduction under dim lighting, small shaded areas, and scanner position variations. Overall, the web-based OMR application provides a practical, efficient, and flexible solution as it can be accessed directly through a browser without requiring additional installations.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id
Thesis advisor	Aditiawan, Firza Prima	NIDN0434010322	firzaprima.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Kus Dwi Prastyo

Date Deposited:

19 Jan 2026 09:03

Last Modified:

20 Jan 2026 01:22

URI:

https://repository.upnjatim.ac.id/id/eprint/48848