Implementation and Evaluation of a Simple On-Device Facial Expression Recognition App Using MIT App Inventor and Personal Image Classifier

Authors

  • Alfin Gimnastiar Universitas Islam Negeri Sumatera Utara Author
  • M. Alfi Syahrin Universitas Islam Negeri Sumatera Utara Author
  • Maulana Firjatullah Universitas Islam Negeri Sumatera Utara Author
  • T Muhammad Ricki Universitas Islam Negeri Sumatera Utara Author
  • Maulana Akbar Universitas Royal Author

Keywords:

emotion recognition, machine learning, Personal Image Classifier, image classification

Abstract

This study presents the implementation and evaluation of a simple on-device facial expression recognition application developed primarily for educational and introductory learning purposes using MIT App Inventor and the Personal Image Classifier (PIC). The application is designed to classify three basic facial expressions angry, sad, and happy using a machine learning model embedded directly into the mobile device. The development process follows a prototyping approach, starting with the design of the user interface, integration of the PIC extension, and the model training workflow, which includes data collection, training, testing, and exporting the trained model for use within the application. The evaluation was conducted through qualitative testing on various facial images obtained from both AI-generated sources and publicly available images. The model successfully produced probability outputs corresponding to each emotion class and demonstrated correct predictions under favorable conditions such as frontal pose and good lighting. However, its overall accuracy remains limited due to the very small training dataset, consisting of only six images, and the absence of data augmentation. These constraints resulted in inconsistent predictions in several test cases. Despite these limitations, the study demonstrates that integrating a lightweight machine learning model into a mobile application using MIT App Inventor is feasible and effective, making it suitable as an accessible learning tool for beginners exploring artificial intelligence and image-based emotion recognition.

References

[1] M. B. Septyono, F. T. Anggraeny, and R. Mumpuni, “Pengenalan Ekspresi Wajah dengan LBP dan Multi-Level CNN,” Jurnal Informatika Polinema, vol. 11, no. 4, pp. 469–476, Aug. 2025, doi: 10.33795/JIP.V11I4.7351.

[2] S. A. Baskara and N. Setiyawati, “Experimental Modeling of Face Emotion Recognition Using Machine Learning Classification (SVM, KNN, Random Forest) and Deep Learning CNN,” Teknika, vol. 14, no. 2, pp. 280–289, Jul. 2025, doi: 10.34148/TEKNIKA.V14I2.1232.

[3] Michelle, S. Birowo, and M. A. Maulana, “Deteksi Suasana Hati Karyawan Berbasis Deep Learning Menggunakan CNN,” bit-Tech, vol. 8, no. 1, pp. 18–24, Aug. 2025, doi: 10.32877/BT.V8I1.1882.

[4] A. N. Inaya, A. U. Rahma, M. Jannah, L. R. K. Arafah, L. L. Ishak, and M. R. Edy, “Klasifikasi Citra Dengan Pendekatan Transfer Learning Pada Gambar Fauna Terbang,” Jurnal MediaTIK, vol. 85, no. 1, pp. 85–89, Jun. 2024, doi: 10.59562/MEDIATIK.V7I1.2785.

[5] I. R. Alfiandi, Gunawan, M. R. Fadhil, and R. Samsinar, “Analisis Performa Convolutional Neural Network (CNN) dan Naive Bayes dalam Face Recognition: Akurasi dan Kompleksitas,” Prosiding Seminar Nasional Hukum, Bisnis, Sains dan Teknologi, vol. 5, no. 1, pp. 284–294, Jan. 2025.

[6] K. Khotimah, F. Yudistira, and M. Ardiansyah, “Efisiensi Deep learning untuk Analisis Data dan Pengambilan Keputusan,” Jurnal Insan Peduli Pendidikan (JIPENDIK), vol. 2, no. 2, pp. 79–82, Dec. 2024.

[7] M. Kholil, R. Akhsani, I. Athaillah, H. Priya Waspada, M. Saiful Muluk, and K. Charisma, “Pelatihan Pengembangan Aplikasi Klasifikasi Gambar Dengan Library Kecerdasan Buatan Bagi Siswa Kelas XI SMAK Diponegoro Blitar – Jawa Timur,” Jurnal Pengabdian Masyarakat Terapan, vol. 1, no. 2, pp. 83–89, Aug. 2024, doi: 10.20884/1.JUPITER.1.2.20.

[8] E. H. Kusuma Dewi, I. S. Pratama, A. S. Putera, and C. Carudin, “Black Box Testing pada Aplikasi Pencatatan Peminjaman Buku Menggunakan Boundary Value Analysis,” STRING (Satuan Tulisan Riset dan Inovasi Teknologi), vol. 6, no. 3, p. 315, Apr. 2022, doi: 10.30998/STRING.V6I3.11958.

[9] F. Dinata and F. Antonio, “ANTESEDEN DARI VIRTUAL ORGANIZATIONAL COMMITMENT DAN DAMPAKNYA TERHADAP VIRTUAL CARE PERFORMANCE (STUDI PADA PLATFORM TELEMEDISIN XYZ DI INDONESIA),” JMBI UNSRAT (Jurnal Ilmiah Manajemen Bisnis dan Inovasi Universitas Sam Ratulangi)., vol. 11, no. 1, pp. 744–765, Mar. 2024, doi: 10.35794/JMBI.V11I1.55630.

[10] S. Siswanto, M. U. Dewi, S. Kholifah, G. Widhiati, and W. Aryani, “Penggunaan Model Deep Learning Untuk Meningkatkan Efisiensi Dalam Aplikasi Machine Learning,” JURNAL PENELITIAN SISTEM INFORMASI (JPSI), vol. 1, no. 4, pp. 215–238, Nov. 2023, doi: 10.54066/JPSI.V1I4.1619.

[11] M. Singh and A. S. Arora, “Varying Illumination and Pose Conditions in Face Recognition,” Procedia Comput Sci, vol. 85, pp. 691–695, Jan. 2021, doi: 10.1016/J.PROCS.2016.05.255.

[12] B. Baso and N. Suciati, “TEMU KEMBALI CITRA TENUN NUSA TENGGARA TIMUR MENGGUNAKAN EKSTRAKSI FITUR YANG ROBUST TERHADAP PERUBAHAN SKALA, ROTASI DAN PENCAHAYAAN,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 7, pp. 349–358, 2021, doi: 10.25126/jtiik.202072002.

[13] S. A. Adzkia and T. Arifin, “Perbandingan Arsitektur CNN Berbasis Transfer Learning untuk Klasifikasi pada BreastMNIST,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 11, no. 2, pp. 192–200, Sep. 2025, doi: 10.25077/TEKNOSI.V11I2.2025.192-200.

[14] A. Taufiq Akbar, S. Saifullah, and H. Prapcoyo, “Klasifikasi Ekspresi Wajah Menggunakan Covolutional Neural Network,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 6, pp. 1399–1412, Dec. 2024, doi: 10.25126/JTIIK.2024118888.

[15] R. Surya, “Peningkatan Akurasi OCR dalam Pemrosesan Formulir Keuangan melalui Fine-Tuning Transformer dan Strategi Pra- pemrosesan Data,” Jurnal Inovasi Informatika, vol. 7, no. 2, pp. 1–12, May 2025, doi: 10.51170/JII.V7I2.85.

[16] T. A. Selian, N. Akbar, and M. I. Hidayat, “Image Classification Based On Color Using Thresholding Method”, jitcos, vol. 1, no. 1, pp. 1–6, Jun. 2025, doi: 10.65230/jitcos.v1i1.5.

[17] M. K. Gibran, E. Budhiarti Nababan and P. Sihombing, "Analysis of Face Recognition with Fuzzy C-Means Clustering Image Segmentation and Learning Vector Quantization," 2020 3rd International Conference on Mechanical, Electronics, Computer, and Industrial Technology (MECnIT), Medan, Indonesia, 2020, pp. 188-193, doi: 10.1109/MECnIT48290.2020.9166649.

[18] S. F. M. . Mar’ah, H. B. P. . Alam, D. Aulia, N. A. . Meliala, F. . Prayoga, and M. K. . Gibran, “Penerapan Teknik Binarisasi Dan Segmentasi Citra Untuk Digitalisasi Tanda Tangan Di Matlab”, JMP, vol. 14, no. 1, pp. 623-630, May 2025.

[19] F. Azmi, M. K. Gibran, and A. Saleh, “Herbal plant image retrieval using HSV color histogram and random forest algorithm,” Journal of Computer Science, Information Technology and Telecommunication Engineering, vol. 6, no. 2, pp. 1019–1027, 2025, doi: 10.30596/jcositte.v6i2.26495.

[20] M. I. Rifki, M. K. Gibran, A. H. Hasugian, and M. D. Solihin, “Pemodelan dan evaluasi prediksi RSRP menggunakan artificial neural network untuk optimasi kualitas layanan jaringan komunikasi nirkabel,” Informatika, vol. 17, no. 1, pp. 392–401, 2025, doi: 10.36723/juri.v17i1.751.

Downloads

Published

31-01-2026

Issue

Vol. 1 No. 1 (2026): Volume 1 Number 1, January 2026

Section

Articles

License

Copyright (c) 2026 Alfin Gimnastiar, M. Alfi Syahrin (Author); Maulana Firjatullah, T Muhammad Ricki (Translator); Maulana Akbar (Author)

Creative Commons License

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

How to Cite

Implementation and Evaluation of a Simple On-Device Facial Expression Recognition App Using MIT App Inventor and Personal Image Classifier. (2026). NextGen Innovations in Computing and Technology, 1(1), 1-10. https://journal.arfadigitech.com/nict/article/view/66

Article Metrics

Abstract Views: 40 times