Comparison of the Use of CNN Methods with SVM for Eye Detection in Car Drivers
DOI:
https://doi.org/10.30743/afmetm24Keywords:
Comparison; Haar Casecade; CNN; SVM; HOG; Kernel; SleepinessAbstract
This study aims to compare the two Convolutional Neural Network (CNN) methods and the Support Vector Machine (SVM) method using Haar Casecade to detect eye patterns, CNN and SVM function to detect eyes in open or close conditions. SVM in the study uses HOG to process images from Haar Casecade so that they can be read by SVM and uses kernels, namely RBF, poly and sigmoid. The case study taken is the detection of sleepy eyes in car drivers using 250 open eye images and 250 closed eye images. The experimental results show that CNN is superior by showing an accuracy value of 98%, precision closed 96% precision open 100%, recall closed 100% and recall open 96%, for F1-score closed and open 98%, while SVM in this study shows an accuracy result of 95% precision close 98% and open 92%, recall close 93% and open 98%, F1-score 95%. This study confirms that the selection of the CNN method is the most appropriate to be used in combination with Haar Casecade because it gets higher accuracy results. These findings can be used as a basis for further development in the drowsiness detection system for car drivers.
References
S. N. Himawan, R. Sohiburroyan, N. B. Nugraha, J. Teknik Informatika, and P. Negeri Indramayu, “Deteksi Kantuk Pengemudi Menggunakan Deep Learning,” Semin. Nas. Ind. dan Teknol. (SNIT), Politek. Negeri Bengkalis, no. November, pp. 1–8, 2022.
R. Boutaba et al., “Open Access A comprehensive survey on machine learning for networking : evolution , applications and research opportunities,” 2018.
T. Zhang et al., “Evaluation of different machine learning models and novel deep learning-based algorithm for landslide susceptibility mapping,” Geosci. Lett., vol. 9, no. 1, 2022.
R. Florez, F. Palomino-Quispe, R. J. Coaquira-Castillo, J. C. Herrera-Levano, T. Paixão, and A. B. Alvarez, “A CNN-Based Approach for Driver Drowsiness Detection by Real-Time Eye State Identification,” Appl. Sci., vol. 13, no. 13, 2023.
R. Andonie and A. C. Florea, “Weighted random search for CNN hyperparameter optimization,” Int. J. Comput. Commun. Control, vol. 15, no. 2, pp. 1–11, 2020.
E. Karypidis, S. G. Mouslech, K. Skoulariki, and A. Gazis, “Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification,” vol. 21, pp. 122–130, 2022.
C. Choi, J. Kim, J. Hyun, Y. Kim, and B. Moon, “Face Detection Using Haar Cascade Classifiers Based on Vertical Component Calibration”.
S. Abidin, “Deteksi Wajah Menggunakan Metode Haar Cascade Classifier Berbasis Webcam Pada Matlab,” J. Teknol. Elekterika, vol. 2, no. 1, p. 21, 2018.
I. Monika Parapat and M. Tanzil Furqon, “Penerapan Metode Support Vector Machine (SVM) Pada Klasifikasi Penyimpangan Tumbuh Kembang Anak,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 10, pp. 3163–3169, 2018, [Online]. Available: http://j-ptiik.ub.ac.id
P. Benchawattananon et al., “Automatic classification of spread ‐ F types in ionogram images using support vector machine and convolutional neural network,” Earth, Planets Sp., 2024.
Y. Albadawi, M. Takruri, and M. Awad, “A Review of Recent Developments in Driver Drowsiness Detection Systems,” Sensors, vol. 22, no. 5, pp. 1–41, 2022.
Y. Ding, “Learning from label proportions for SAR image classification,” 2017, doi: 10.1186/s13634-017-0478-8.
H. Naeem, B. M. Alshammari, and F. Ullah, “Explainable Artificial Intelligence-Based IoT Device Malware Detection Mechanism Using Image Visualization and Fine-Tuned CNN-Based Transfer Learning Model,” Comput. Intell. Neurosci., vol. 2022, 2022.
H. J. Jie and P. Wanda, “Runpool: A dynamic pooling layer for convolution neural network,” Int. J. Comput. Intell. Syst., vol. 13, no. 1, pp. 66–76, 2020.
H. Darmanto, D. Learning, T. Learning, and G. Descent, “PENGENALAN SPESIES IKAN BERDASARKAN KONTUR OTOLITH,” vol. 2, 2019.
Y. Chen et al., “Deep Learning – Based Brain Computed Tomography Image Classification with Hyperparameter Optimization through Transfer Learning for Stroke,” 2022.
M. Azzam Al Fauzie and J. Akhir Putra, “Clustering Data Menggunakan Metode K-Means untuk Rekomendasikan Pembelajaran Akademik bagi Siswa Aktif dalam Ekstrakurikuler,” KLIK Kaji. Ilm. Inform. dan Komput., vol. 4, no. 1, pp. 642–648, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 M. Khairul Ikhsan, Roslina, Rika Rosnelly
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
