Klasifikasi Bentuk Wajah Menggunakan Algoritma CNN Dengan Arsitektur Densenet-201
Abstract
Face shape classification is an important component in various face recognition–based applications, such as security systems, social media personalization, and style recommendation systems. However, accurate face shape classification remains a challenge due to the complex variations in facial morphological structures, such as oval, square, heart, oblong, and round shapes. This study uses a Convolutional Neural Network (CNN) algorithm with the DenseNet-201 architecture. The collected dataset consists of 5,000 facial images categorized into Oval, Round, Square, Heart, and Oblong, with a data split of 80% for training and 20% for testing. The model was then trained using the DenseNet-201 architecture and evaluated using two different learning rates (0.001 and 0.0001), two batch sizes (16 and 32), and 50 and 100 epochs. The initial results showed a model accuracy of 42%, with a tendency to classify face images as the square category. Subsequently, an additional experiment was conducted, which successfully achieved an accuracy of 89%.
Keywords: Facial shape; Convolutional Neural Network; DenseNet-201; Facial classification
Abstrak
Klasifikasi bentuk wajah merupakan komponen penting dalam berbagai aplikasi berbasis pengenalan wajah, seperti sistem keamanan, personalisasi media sosial, hingga sistem rekomendasi gaya. Namun, pengklasifikasian bentuk wajah secara akurat masih menjadi tantangan karena adanya variasi kompleks dalam struktur morfologi wajah, seperti bentuk oval, persegi, hati, oblong dan bulat. Penelitian ini menggunakan algoritma CNN dengan arsitektur DenseNet-201. Dataset yang dikumpulkan sebanyak 5000 gambar wajah, dengan kategori (Oval, Round (Bulat), Square (Persegi), Heart (Hati), dan Oblong/lonjong), dengan masing-masing proporsi 80% data Training dan 20% data Testing. Kemudian model dilatih dengan arsitektur DenseNet-201 dan dilakukan uji coba dengan dua nilai learning rate yang berbeda 0.001 dan 0.0001, dua ukuran batch 16 dan 32, dan epoch 50 dan 100. Hasil akurasi model yang di dapatkan sebesar 42% dengan kecenderungan model klasifikasi citra bentuk wajah square. Lalu dilakukan eksperimen tambahan yang berhasil mendapatkan akurasi sebesar 89%.
Keywords
References
S. Sohail, G. Anjum, and M. Aziz, “Hijab and enclothed cognition: The effect of hijab on interpersonal attitudes in a homogenous Muslim-majority context,” Cogent Psychol., vol. 10, no. 1, pp. 1–19, 2023, doi: 10.1080/23311908.2023.2219084.
M.Y. Putra, “Rancang Bangun Deteksi Bentuk Wajah Untuk Menentukan Gaya Rambut Menggunakan Algoritma CNN,” Repeater Publ. Tek. Inform. dan Jar., vol. 2, no. 3, pp. 206–212, 2024, doi: 10.62951/repeater.v2i3.139.
A. E. D. Tio, “Face shape classification using Inception v3,” 2019. doi: 10.48550/arXiv.1911.07916.
P. Chao, C. Y. Kao, Y. Ruan, C. H. Huang, and Y. L. Lin, “HarDNet: A low memory traffic network,” in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 1–10. doi: 10.1109/ICCV.2019.00365.
F. D. A. D. P. R. M. Wibowo and A. Jayadi, “A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face,” JUITA J. Inform., vol. 9, no. 1, pp. 115–122, 2021, doi: 10.30595/juita.v9i1.9624.
A. J. M. F. Novriandy, B. Rahmat, “Klasikasi Citra Pada Penyakit Kanker Mulut Menggunakan Arsitektur Densenet201 Menggunakan Optimasi Adam Dan Sgd,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 4, pp. 6132–6140, 2024, doi: 10.36040/jati.v8i4.10077.
K. L. Kohsasih, M. D. Agung Rizky, T. Fahriyani, V. Wijaya, and R. Rosnelly, “Analisis Perbandingan Algoritma Convolutional Neural Network Dan Algoritma Multi-Layer Perceptron Neural Dalam Klasifikasi Citra Sampah,” J. TIMES, vol. 10, no. 2, pp. 22–28, 2022, doi: 10.51351/jtm.10.2.2021655.
R. P. P. Kusdiananggalih, E. Rachmawati, “Pengenalan Ekspresi Wajah Dari Cross Dataset Menggunakan Convolutional Neural Network (CNN),” J. Tugas Akhir Fak. Inform., vol. 8, no. 2, pp. 3429–3445, 2021.
S. S. K. JASMAN PARDEDE and Department, “Face Race Classification using ResNet-152 and DenseNet- 121,” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 12, no. 3, pp. 798–809, 2024, doi: 10.26760/elkomika.v12i3.798.
I. W. W. Premanandara and I. G. A. Wibawa, “Klasifikasi Bentuk Wajah Manusia Menggunakan Metode Convolutional Neural Network (CNN),” J. Nas. Teknol. Inf. dan Apl. Klasifikasi, vol. 1, no. 1, pp. 373–378, 2022.
G. E. P. Purba, S. H. Wijoyo, and N. Y. Setiawan, “Pengaruh Transfer Learning Resnet Dan Densenet Terhadap Performa Klasifikasi Ekspresi Wajah Menggunakan Dataset Fer-2013,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 1, pp. 1–9, 2017, [Online]. Available: http://j-ptiik.ub.ac.id
R. A. Karisma and F. D. Adhinata, “Transfer Learning with Densenet201 Architecture Model for Potato Leaf Disease Classification,” ICCoSITE 2023 - Int. Conf. Comput. Sci. Inf. Technol. Eng. Digit. Transform. Strateg. Facing VUCA TUNA Era, pp. 738–743, 2023, doi: 10.1109/ICCoSITE57641.2023.10127772.
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017, pp. 1–9. doi: 10.1109/CVPR.2017.243.
S.D. Chandra, H. Oktavianto, and A.K. Wardoyo, “Klasifikasi Malware Menggunakan Metode Convolutional Neural Network (CNN) Berbasis Website,” J. Penelit. Teknol. Inf. dan Sains, vol. 2, no. 2, pp. 84–99, 2024, doi: 10.54066/jptis.v2i2.1931.
M. Khaliqah, L. Sarifah, and S. Khotijah, “Implementasi Algoritma K-Nearest Neighbor (K-NN) dalam Mengklasifikasikan Berbagai Jenis Ekspresi Wajah Manusia,” Zeta - Math J., vol. 9, no. 1, pp. 10–20, 2024, doi: 10.31102/zeta.2024.9.1.10-20.
How To Cite This :
Refbacks
- There are currently no refbacks.
