EVALUASI KINERJA KOMPUTER MIKRO RASPBERRY PI DENGAN PEMBELAJARAN MESIN UNTUK PENGENALAN WAJAH
DOI:
https://doi.org/10.36080/skanika.v9i1.3649Kata Kunci:
CNN, Pembelajaran mesin, Pengenalan wajah, Raspberry Pi, SVMAbstrak
Implementasi sistem pengenalan wajah pada perangkat tertanam seringkali dibatasi oleh sumber daya komputasi yang terbatas dan biaya hardware yang tinggi. Studi ini bertujuan untuk mengevaluasi dan membandingkan kinerja algoritma Support Vector Machine (SVM) dan Convolutional Neural Network (CNN) pada mikrokomputer Raspberry Pi 4B. Metode penelitian melibatkan pengujian arsitektur CNN dan kernel SVM pada dataset Kaggle yang terdiri dari 2.000 gambar wajah dari lima kelas identitas. Parameter evaluasi yang digunakan meliputi akurasi, presisi, recall, F-Score, penggunaan sumber daya (CPU/RAM), dan kecepatan inferensi. Hasil pengujian menunjukkan bahwa algoritma CNN mencapai akurasi tertinggi sebesar 93%, namun memerlukan waktu inferensi yang lebih lama, yaitu rata-rata 268.52 ms per citra. Di sisi lain, SVM mencapai akurasi 87% dengan waktu inferensi yang jauh lebih cepat, yaitu rata-rata 8.02 ms per citra. Berdasarkan hasil uji, studi ini menyimpulkan bahwa meskipun CNN unggul dalam akurasi, SVM lebih direkomendasikan untuk aplikasi sistem biometrik real-time pada mikrokomputer karena efisiensi waktu komputasi dan penggunaan sumber daya yang lebih rendah.
Unduhan
Referensi
[1] M. S. Kabisha, K. A. Rahim, M. Khaliluzzaman, and S. I. Khan, “Face and Hand Gesture Recognition Based Person Identification System using Convolutional Neural Network,” Int. J. Intell. Syst. Appl. Eng., vol. 10, no. 1, pp. 105–115, 2022, doi: 10.18201/ijisae.2022.273.
[2] W. Boukhari, M. Benyettou, and B. Abderrahim, “A human vision based system for biometric images recognition,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 3, pp. 1508–1517, 2022, doi: 10.11591/ijeecs.v25.i3.pp1508-1517.
[3] Y. Aufar and I. S. Sitanggang, “Face recognition based on Siamese convolutional neural network using Kivy framework,” Indones. J. Electr. Eng. Comput. Sci., vol. 26, no. 2, pp. 764–772, 2022, doi: 10.11591/ijeecs.v26.i2.pp764-772.
[4] Q. Sun and A. Redei, “Knock Knock, Who’s There: Facial Recognition using CNN-based Classifiers,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 1, pp. 9–16, 2022, doi: 10.14569/IJACSA.2022.0130102.
[5] J. Almotiri, “Face Recognition using Principal Component Analysis and Clustered Self-Organizing Map,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 3, pp. 509–520, 2022, doi: 10.14569/IJACSA.2022.0130361.
[6] C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning,” Electron. Mark., vol. 31, no. 3, pp. 685–695, 2021, doi: 10.1007/s12525-021-00475-2.
[7] A. Yadav, E. Kumar, and P. K. Yadav, “Object detection and used car price predicting analysis system (UCPAS) using machine learning technique,” Linguist. Cult. Rev., vol. 5, no. S2, pp. 1131–1147, 2021, doi: 10.21744/lingcure.v5ns2.1660.
[8] M. Muslih and E. H. Rachmawanto, “Convolutional Neural Network (Cnn) Untuk Klasifikasi Citra Penyakit Diabetes Retinopathy,” SKANIKA, vol. 5, no. 2, pp. 167–176, 2022, doi: 10.36080/skanika.v5i2.2945.
[9] C. Durán et al., “Nonlinear machine learning pattern recognition and bacteria-metabolite multilayer network analysis of perturbed gastric microbiome,” Nat. Commun., vol. 12, no. 1, 2021, doi: 10.1038/s41467-021-22135-x.
[10] P. Chandirasekeran and S. Shridevi, “Smart Elevator Obstruction Detection System using Image Classification,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 4, pp. 134–141, 2022, doi: 10.14569/IJACSA.2022.0130416.
[11] A. Fadlil, R. Umar, Sunardi, and A. S. Nugroho, “Comparison of Machine Learning Approach for Waste Bottle Classification,” Emerg. Sci. J., vol. 6, no. 5, pp. 1075–1085, 2022, doi: 10.28991/ESJ-2022-06-05-011.
[12] M. Trigka and E. Dritsas, “A Comprehensive Survey of Deep Learning Approaches in Image Processing,” Sensors, vol. 25, no. 2, 2025, doi: 10.3390/s25020531.
[13] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,” IEEE Trans. Neural Networks Learn. Syst., vol. 33, no. 12, pp. 6999–7019, 2021, doi: https://doi.org/10.1109/TNNLS.2021.3084827.
[14] M. Kanthi, T. H. Sarma, and C. S. Bindu, “Multi-scale 3D-convolutional neural network for hyperspectral image classification,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 1, pp. 307–316, 2022, doi: 10.11591/ijeecs.v25.i1.pp307-316.
[15] S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, and D. J. Inman, “1D convolutional neural networks and applications: A survey,” Mech. Syst. Signal Process., vol. 151, pp. 1–21, 2021, doi: https://doi.org/10.1016/j.ymssp.2020.107398.
[16] J. Yang, T. Qian, F. Zhang, and S. U. Khan, “Real-Time Facial Expression Recognition Based on Edge Computing,” IEEE Access, vol. 9, pp. 76178–76190, 2021, doi: 10.1109/ACCESS.2021.3082641.
[17] E. Gamess and S. Hernandez, “Performance Evaluation of Different Raspberry Pi Models for a Broad Spectrum of Interests,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 2, pp. 819–829, 2022, doi: https://dx.doi.org/10.14569/IJACSA.2022.0130295.
[18] J. W. Jolles, “Methods Ecol Evol - 2021 - Jolles - Broad‐scale applications of the Raspberry Pi A review and guide for biologists.pdf,” Methods Ecol. Evol., vol. 12, no. 9, pp. 1562–1579, 2021.
[19] A. Magdi, N. A. Lashin, and O. El-komy, “Robust color image watermarking using multi-core Raspberry pi cluster,” Multimed. Tools Appl., pp. 17185–17204, 2022.
[20] A. S. Nugroho, R. Umar, and A. Fadlil, “Klasifikasi Botol Plastik Menggunakan Multiclass Support Vector Machine,” J. Khatulistiwa Inform., vol. 9, no. 2, pp. 79–85, 2021, doi: 10.31294/jki.v9i2.11058.
[21] S. B. Sapin, B. A. Alibudbud, P. B. Molleno, M. B. Veluz, and J. R. Asor, “Intelligent aquaculture system for pisciculture simulation using deep learning algorithm,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 1, pp. 561–568, 2022, doi: 10.11591/ijeecs.v25.i1.pp561-568.
[22] A. E. Minarno, M. H. C. Mandiri, Y. Azhar, F. Bimantoro, H. A. Nugroho, and Z. Ibrahim, “Classification of Diabetic Retinopathy Disease Using Convolutional Neural Network,” Int. J. Informatics Vis., vol. 6, no. 1, pp. 12–18, 2022, doi: 10.30630/joiv.6.1.857
[23] S. M. Abas, A. M. Abdulazeez, and D. Q. Zeebaree, “A YOLO and convolutional neural network for the detection and classification of leukocytes in leukemia,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 1, pp. 200–213, 2022, doi: 10.11591/ijeecs.v25.i1.pp200-213.
[24] M. Bansal, M. Kumar, M. Sachdeva, and A. Mittal, “Transfer learning for image classification using VGG19: Caltech-101 image data set,” J. Ambient Intell. Humaniz. Comput., no. 0123456789, 2021, doi: 10.1007/s12652-021-03488-z.
[25] S. Patel, R. Patel, N. Ganatra, and A. Patel, “Spatial Feature Fusion for Biomedical Image Classification based on Ensemble Deep CNN and Transfer Learning,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 5, pp. 153–159, 2022.
[26] J. Wang, X. Jing, Z. Yan, Y. Fu, W. Pedrycz, and L. T. Yang, “A Survey on Trust Evaluation Based on Machine Learning,” ACM Comput. Surv., vol. 53, no. 5, 2020.
[27] A. Huc, J. Salej, and M. Trebar, “Analysis of Machine Learning Algorithms for Anomaly Detection on Edge Devices,” Sensors, vol. 21, no. 14, pp. 1–22, 2021.
[28] N. Bartwal, “Celeb Faces Attributes Dataset (CelebA),” Kaggle. Accessed: Jul. 20, 2025. [Online]. Available: https://www.kaggle.com/datasets/nikhilbartwal001/celeba
[29] M. S. Sayeed, P. P. Min, and M. A. Bari, “Deep Learning Based Gait Recognition Using Convolutional Neural Network in the COVID-19 Pandemic,” Emerg. Sci. J., vol. 6, no. 5, pp. 1086–1099, 2022, doi: 10.28991/ESJ-2022-06-05-012.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Denis Prayogi
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
CC BY-SA 4.0
Creative Commons Attribution-ShareAlike 4.0 International
This license requires that reusers give credit to the creator. It allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, even for commercial purposes. If others remix, adapt, or build upon the material, they must license the modified material under identical terms.
BY: Credit must be given to you, the creator.
SA: Adaptations must be shared under the same terms.ng
