Paper: arXiv 2512.17895
Authors: Wisnu Uriawan, Ahmad Badru Al Husaeni, Dzakwanfaiq Nauval, Farid Muhtar Fathir, Mahesa Adlan Falah, Muhammad Miftahur Rizki Awalin
Abstract
This study presents the development of a marker-based augmented reality (AR) application designed to visualize the content of Surah al-Fil as an interactive and context-rich medium for Islamic education. Using a research and development approach, the system was developed through structured stages including data collection, user requirement analysis, interface design, 3D asset creation using Blender, and integration of Unity 3D with the Vuforia SDK. The application features key visual elements such as the elephant army, the Kaaba, and the Ababil birds, which were modeled in detail and linked to high-contrast image markers to ensure accurate and stable AR tracking. Functional testing demonstrated strong technical performance, achieving a 95 percent marker detection accuracy at an optimal distance of 30-40 cm with consistent real-time rendering across multiple Android devices. User evaluations involving students and Islamic education teachers indicated high acceptance, with an overall satisfaction score of 4.7 out of 5 in terms of usability, visual appeal, interactivity, and learning effectiveness. These findings indicate that AR-based learning media can enhance learner engagement, deepen understanding of Quranic narratives, and provide immersive insights into historical and spiritual contexts. Overall, this study demonstrates that marker-based AR technology has significant potential to support innovation in digital Islamic education by enriching traditional learning with interactive and visually intuitive experiences.
Complexity vs Empirical Score
- Math Complexity: 0.0/10
- Empirical Rigor: 8.5/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper contains no advanced mathematics or formulas, relying instead on software development methodologies and user surveys. It includes detailed empirical validation with specific metrics like 95% marker detection accuracy, user satisfaction scores (4.7/5), and performance testing across devices, making it highly backtest-ready in the context of educational technology.
Research Flowchart
flowchart TD
A["Research Goal: Develop AR App to Visualize<br>Surah al-Fil's Content for Education"] --> B["Methodology: R&D with Data Collection<br>& User Requirement Analysis"]
B --> C["Inputs: Quranic Narratives &<br>User Needs Assessment"]
C --> D["Computational Process: 3D Modeling Blender<br>& Unity/Vuforia Integration"]
D --> E{"Testing & User Evaluation"}
E -- Performance --> F["95% Marker Accuracy<br>at 30-40 cm Distance"]
E -- User Feedback --> G["4.7/5 Satisfaction<br>High Engagement & Learning"]
F --> H["Outcome: Validated AR App for<br>Immersive Islamic Education"]
G --> H
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a marker-based augmented reality application that visualizes the content of Surah al‑Fiil for interactive Islamic education.
Source sentence
This study presents the development of a marker-based augmented reality (AR) application designed to visualize the content of Surah al-Fil as an interactive and context-rich medium for Islamic education.
Assumes
No explicit assumptions found in the text.
Data
- marker database other unknown
Source sentence
The marker is then registered in the Vuforia Target Manager database so that it can be accurately recognized by the tracking algorithm. In this study, Vuforia was used to: 1) Create and manage the marker database in the Vuforia Target Manager, which contains image markers such as illustrations of the Kaaba, the elephant army, and the Ababil birds.
Costs
Not applicable
Finds 5
- Marker detection accuracy reaches 95 % at an optimal distance of 30–40 cm. performance
Source sentence
Functional testing demonstrated strong technical performance, achieving a 95 percent marker detection accuracy at an optimal distance of 30-40 cm with consistent real-time rendering across multiple Android devices. The testing results demonstrate that the system is capable of detecting markers with high accuracy, reaching 95% at an optimal distance of 30–40 cm, while displaying stable 3D animations synchronized with
- Under bright lighting (600–800 lux) detection accuracy is 97 %; under medium lighting (300–500 lux) it remains 95 %, but drops to 82 % in low lighting (<150 lux) with detection time increasing to 2.1 seconds. performance figure from elsewhere in the paper
Source sentence
Under bright lighting (600–800 lux), marker detection accu-racy reached 97%. Under medium lighting conditions (300–500 lux), accuracy remained high at 95%.
- User evaluations show a high overall satisfaction score of 4.7 out of 5 for usability, visual appeal, interactivity, and learning effectiveness. statistical
Source sentence
User evaluations involving students and Islamic education teachers indicated high acceptance, with an overall satisfaction score of 4.7 out of 5 in terms of usability, visual appeal, interactivity, and learning effectiveness. The application interface was assessed as easy to understand, with an average user satisfaction score of 4.7 out of a 5-point scale.
- The system maintains stable tracking when the device is tilted up to 35 degrees, but detection becomes harder at steeper angles. performance
Source sentence
Additional observations also revealed that the system maintained stable tracking when the device was tilted up to 35 degrees, although at steeper angles the marker became harder to detect.
- High‑resolution markers (300 DPI) yield the best tracking results, while low‑resolution prints can cause jitter and instability. performance
Source sentence
When tested with various marker print qualities, high-resolution markers (300 DPI) showed the best results, while low-resolution prints occasionally produced jitter.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 16 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.