Pendeteksi Objek Berbasis Suara Menggunakan CNN pada Perangkat Android sebagai Asisten Visual Bagi Tunanetra

Authors

  • Fernanda Ma'rouf Universitas Nusantara PGRI Kediri Indonesia
  • Risky Aswi Ramadhani Universitas Nusantara PGRI Kediri Indonesia
  • Lilia Sinta Wahyuniar Universitas Nusantara PGRI Kediri Indonesia

DOI:

https://doi.org/10.29407/61hsq887

Abstract

Penelitian ini mengembangkan aplikasi deteksi objek berbasis mobile untuk pengguna tunanetra, menggunakan kamera ponsel sebagai input visual. Model deteksi menggunakan arsitektur Convolutional Neural Network (CNN) yang telah dikonversi ke format TensorFlow Lite (.tflite) untuk efisiensi di perangkat Android. Hasil deteksi objek diproses dan diterjemahkan ke dalam output audio menggunakan modul Text-to-Speech (TTS) bawaan Android. Aplikasi diuji dalam berbagai kondisi pencahayaan (terang, redup, dan alami) serta latar belakang (sederhana dan kompleks), dengan metrik evaluasi berupa akurasi deteksi dan waktu respons audio. Rata-rata akurasi deteksi mencapai 88,7% dalam ruangan dan 83,2% di luar ruangan, dengan latency sekitar 1,2 detik per deteksi-audio. Sistem dirancang untuk mendeteksi multi-objek dalam satu frame dan menyuarakannya secara berurutan. Platform dikembangkan menggunakan Kotlin, dengan minimum spesifikasi perangkat: Android 8.0 dan RAM 2GB.

Keywords:

Android, CNN, Deteksi objek, Text-to-Speech, Tunanetra

##plugins.themes.default.displayStats.downloads##

##plugins.themes.default.displayStats.noStats##

References

[1] I. W. R. Putra & I. G. N. A. Santosa. (2023). Penerapan YOLOv8 untuk Deteksi Objek

pada Sistem Monitoring Berbasis Kamera. Jurnal Teknologi dan Sistem Komputer, 11(1),

45–53.

[2] Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement.

arXiv:1804.02767.

[3] Deng, J., Guo, J., & Zafeiriou, S. (2020). ArcFace: Additive Angular Margin Loss for

Deep Face Recognition. IEEE/CVF Conference on Computer Vision and Pattern

Recognition (CVPR), 4690–4699.

[4] TensorFlow. (2023). TensorFlow Lite | Deploy machine learning models on mobile and

edge devices. https://www.tensorflow.org/lite

[5] Google Developers. (2023). Text-to-Speech Overview | Android Developers. Diakses

dari: https://developer.android.com/reference/android/speech/tts/TextToSpeech

[6] WHO. (2021). World report on vision. World Health Organization.

https://www.who.int/publications/i/item/world-report-on-vision

[7] S. R. Abdi & A. Wijaya. (2021). Implementasi Convolutional Neural Network dalam

Pendeteksi Objek untuk Difabel Netra. Jurnal Teknologi Informasi dan Ilmu Komputer,

8(2), 210–218.

[8] Lin, T.-Y., Maire, M., Belongie, S., et al. (2015). Microsoft COCO: Common Objects in

Context. European Conference on Computer Vision (ECCV), 740–755.

[9] Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for

Deep Learning. Journal of Big Data, 6(1), 60.

[10] David, R., Duke, B., Jain, A., et al. (2021). TensorFlow Lite Micro: Embedded Machine

Learning on TinyML Systems. Proceedings of Machine Learning and Systems (MLSys),

3, 800–811.

[11] Hidayatullah, M., & Prasetyo, E. (2022). Evaluasi Kinerja Aplikasi Mobile Berbasis

TensorFlow Lite untuk Deteksi Objek. Jurnal Ilmiah Teknik Informatika, 10(3), 35–42.

Downloads

Published

2026-07-20

Issue

Vol. 10 No. 2 (2026): Prosiding Seminar Nasional Inovasi Teknologi Tahun 2026

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this journal agree to the following terms:

  1. Copyright on any article is retained by the author(s).
  2. The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
  3. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  4. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
  5. The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License

How to Cite

Pendeteksi Objek Berbasis Suara Menggunakan CNN pada Perangkat Android sebagai Asisten Visual Bagi Tunanetra. (2026). Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), 10(2), 1215-1221. https://doi.org/10.29407/61hsq887