Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69046
Volume:
10 |
11 |
Nov 2026
Pages:
1-8
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Computer Science and Engineering
KLS Vishwanathrao Deshpande Institute of Technology Haliyal

Computer Science and Engineering
KLS Vishwanathrao Deshpande Institute of Technology Haliyal

Computer Science and Engineering
KLS Vishwanathrao Deshpande Institute of Technology Haliyal

Computer Science and Engineering
KLS Vishwanathrao Deshpande Institute of Technology Haliyal

Computer Science and Engineering
KLS Vishwanathrao Deshpande Institute of Technology Haliyal
Blind and visually impaired people face persistent difficulty in identifying nearby objects, reading printed text, determining their location, and summoning help. Existing assistive applications usually address only one of these needs. This paper presents TRIVEX, a native Android application that integrates real-time object detection, scene description, text reading, location assistance, and emergency support behind a voice-first interface. Camera frames are analyzed on the device by a YOLO26n model executed through ONNX Runtime, printed text is recognized by Tesseract, and spoken commands are decoded by Vosk. Results are delivered through Android Text-to-Speech in English, Hindi, Kannada, Marathi, or Telugu. An optional cloud model supplies contextual scene descriptions when connectivity is available, and an SOS module calls a trusted contact and sends the user’s location by SMS. Functional testing on a smartphone confirmed the reading, location, emergency, and voice-command workflows. Detection accuracy, response latency, and usability were not measured quantitatively; an evaluation protocol for these properties is outlined.
KEYWORDS
TRIVEX brings object detection, scene description, text reading, location assistance, and emergency signalling into a single Android application that is operated by voice and answers in speech. Its design executes the YOLO26n detector, Tesseract, and the Vosk recognizer on the device, reserves cloud processing for optional scene description, and stores only five local settings. Functional testing confirmed the reading, location, emergency, and voice-command workflows on a smartphone. The application uses only the built-in camera, microphone, speaker, and positioning hardware, which keeps it affordable. Its value to visually impaired users nevertheless remains to be demonstrated through quantitative measurement of accuracy and latency and through a usability study with the intended users, which are the next steps of this work.
1. World Health Organization, “Blindness and vision impairment,” fact sheet, Feb. 10, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment Recognit. (CVPR), 2016, pp. 779–788, doi: 10.1109/CVPR.2016.91. 2. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern 3. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020. 4. R. Sapkota, R. H. Cheppally, A. Sharda, and M. Karkee, “YOLO26: Key architectural enhancements and performance benchmarking for real-time object detection,” arXiv:2509.25164, 2025. 5. N. Rachburee and W. Punlumjeak, “An assistive model of obstacle detection based on deep learning: YOLOv3 for visually impaired people,” Int. J. Elect. Comput. Eng., vol. 11, no. 4, pp. 3434–3442, Aug. 2021, doi: 10.11591/ijece.v11i4.pp3434-3442. 6. K. S. M. Anbananthen et al., “The Eye: A light weight mobile application for visually challenged people using improved YOLOv5l algorithm,” Emerg. Sci. J., vol. 7, no. 5, pp. 1636–1652, Oct. 2023, doi: 10.28991/ESJ- 2023-07-05-011. 7. K. D. Bamane et al., “Enhancement in real time deep learning object detection and direction prediction for visually impaired using YOLO and OpenCV,” Int. J. Intell. Syst. Appl. Eng., vol. 12, no. 3, pp. 887–892, 2024. 8. R. C. Joshi, S. Yadav, M. K. Dutta, and C. M. Travieso-Gonzalez, “Efficient multi-object detection and smart navigation using artificial intelligence for visually impaired people,” Entropy, vol. 22, no. 9, Art. no. 941, 2020, doi: 10.3390/e22090941. 9. A. Aralikatti, J. Appalla, S. Kushal, G. S. Naveen, S. Lokesh, and B. S. Jayasri, “Real-time object detection and face recognition system to assist the visually impaired,” J. Phys.: Conf. Ser., vol. 1706, no. 1, 2020. 10. N. Jawaid, A. Warsi, A. A. Shaikh, and M. Yahya, “Object detection and narrator for visually impaired people,” in Proc. IEEE 6th Int. Conf. Eng. Technol. Appl. Sci. (ICETAS), 2019.
Publication Date
11/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...