The Effect of Layer Batch Normalization and Droupout of CNN model Performance on Facial Expression Classification

- Norhikmah - University AMIKOM Yogyakarta, Daerah Istimewa Yogyakarta, 55283, Indonesia
Afdhal Lutfhi - University AMIKOM Yogyakarta, Daerah Istimewa Yogyakarta, 55283, Indonesia
- Rumini - University AMIKOM Yogyakarta, Daerah Istimewa Yogyakarta, 55283, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.6.2-2.921

Abstract


One of the implementations of face recognition is facial expression recognition in which a machine can recognize facial expression patterns from the observed data. This study used two models of convolutional neural network, model A and model B. The first model A was without batch normalization and dropout layers, while the second model B used batch normalization and dropout layers. It used an arrangement of 4 layer models with activation of ReLU and Softmax layers as well as 2 fully connected layers for 5 different classes of facial expressions of angry, happy, normal, sad, and shock faces. Research Metodology are 1). Data Analysis, 2). Preprocessing grayscaling, 3). Convolutional Neural Network (CNN), 4). Model validation Testing, Obtained an accuracy of 64.8% for training data and accuracy of 63.3% for validation data. The use of dropout layers and batch normalization could maintain the stability of both training data and validation data so that there was no overfitting. By dividing the batch size on the training data into 50% with 200 iterations, aiming to make the load on each training model lighter, by using the learning rate to be 0.001 which works to improve the weight value, thus making the training model work to be fast without crossing the minimum error limit. Accuracy results in the classification of ekp facial receipts from the distance of the camera to the face object about 30 cm in the room with the use of bright enough lighting by 78%.


Keywords


Face recognition; facial expression; batch normalization; dropout layer ; convolutional neural network

Full Text:

PDF

References


W. S. Eka Putra, “Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN) pada Caltech 101,” J. Tek. ITS, vol. 5, no. 1, 2016, doi: 10.12962/j23373539.v5i1.15696.

A. A. Marunduh and Lina, “Klasifikasi Emosi Pada Wajah Dari Rekaman Aplikasi Video Conference Dengan Menggunakan Metode Convolutional Neural Network” J. Ilmu Komput. dan Sist. Inf., vol. 09, pp. 27–31, 2021.

N. Inzani, R. Amalia, and J. Y. Sari, “Mengidentifikasi Mood Mahasiswa Berdasarkan Ekspresi Wajah dengan Menggunakan Discrete Wavelet Transform dan Fuzzy K-Nearest Neighbor,” vol. XI, no. 1, pp. 34–38, 2019.

Lia Farokhah, “Implementasi Convolutional Neural Network untuk Klasifikasi Variasi Intensitas Emosi pada Dynamic Image Sequence,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 6, pp. 1070–1076, 2020, doi: 10.29207/resti.v4i6.2644.

M. Zufar and B. Setiyono, “Convolutional Neural Networks Untuk Pengenalan Wajah Secara Real-Time,” J. Sains dan Seni ITS, vol. 5, no. 2, p. 128862, 2016, doi: 10.12962/j23373520.v5i2.18854.

A. T. Lopes, E. De Aguiar, and T. Oliveira-Santos, “A Facial Expression Recognition System Using Convolutional Networks,” Brazilian Symp. Comput. Graph. Image Process., vol. 2015-Octob, no. August 2005, pp. 273–280, 2015, doi: 10.1109/SIBGRAPI.2015.14.

A. W. Wibowo, A. Karima, Wiktasari, A. Yobioktabera, and S. Fahriah, “Pendeteksian dan Pengenalan Wajah Pada Foto Secara Real Time Dengan Haar Cascade dan Local Binary Pattern Histogram,” JTET (Jurnal Tek. Elektro Ter., vol. Vol. 9 No., pp. 6 – 11, 2020.

L. M. R. Rere, R. Dalam, and K. Baru, “Studi Pengenalan Ekspresi Wajah Berbasis Convolutional Neural Network,” vol. 3, 2019.

P. Daru, S.'U,Shofwatul."Penentuan Emosi Pada Video Dengan Convotional Neural Network" JISKA (Jurnal Informatika Sunan Kalijaga), vol. 5, no. 1, p. 23, 2020, doi: 10.14421/jiska.2020.51-04.

N. Sofia, “Convolutional Neural Network,” Medium.com, 2018. https://medium.com/@nadhifasofia/1-convolutional-neural-network-convolutional-neural-network-merupakan-salah-satu-metode-machine-28189e17335b.

K. Fukushima, “Neocognitron: A self-organizing neuralnetwork model for a mechanism of pattern recognition unaffected by shift in position,” Biol. Cybern., vol. 36, no. 4, pp. 193–202, 1980, doi: 10.1007/BF00344251.

Cs231n.stanford.edu, “CS231n: Convolutional Neural Networks for Visual Recognition,” 2021. https://cs231n.github.io/classification/

S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” 32nd Int. Conf. M

S. Nitish and H. Geoffrey, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Phys. Lett. B, vol. 299, no. 3–4, pp. 345–350, 1993, doi: 10.1016/0370-2693(93)90272-J

A. Yusuf, R. Cahya Wihandika, and C. Dewi, “Klasifikasi Emosi Berdasarkan Ciri Wajah Menggunakan Convolutional Neural Network,” 2019. [Online]. Available: http://j-ptiik.ub.ac.id

F. M. Qotrunnada and P. H. Utomo, “Metode Convolutional Neural Network untuk Klasifikasi Wajah Bermasker,” Prosiding Seminar Nasional Matematika, vol. 5, pp. 799–807, 2022, [Online].Available:https://journal.unnes.ac.id/sju/index.php/prisma

Q. Zhang, M. Zhang, T. Chen, Z. Sun, Y. Ma, and B. Yu, “Recent advances in convolutional neural network acceleration,” Neurocomputing, vol. 323, pp. 37–51, 2017, doi: 10.1016/j.neucom.2018.09.038.

Dharmadi.R.“Mengenal Covutional Layer dan Pooling Layer,” 2018 https://medium.com/nodeflux/mengenal-convolutional-layer-dan-pooling-layer-3c6f5c393ab2

Warnia,N , “CNN Modelling Untuk Deteksi Wajah Berbasis Gender Menggunakan Python,” Jurnal Politeknik Caltex Riau, vol. 2, pp. 192–199, 2020.

Nurkhasanah and Murinto, “Klasifikasi Penyakit Kulit Wajah Menggunakan Metode Convolutional Neural Network Classification of Facial Skin Diseases Using the Method of the Convolutional Neural Network,” SAINTEKS, vol. 18, no. 2, 2021, [Online]. Available: https://www.kaggle.com/datasets

A. Kholik, “Klasifikasi Menggunakan CNN pada Tangkapan Layar Halaman Instagram” JDMSI, vol. 2, no. 2, pp. 10–20, 2021.

C. Garbin, X. Zhu, and O. Marques, “Dropout vs. batch normalization: an empirical study of their impact to deep learning,” Multimedia Tools and Applications, vol. 79, no. 19–20, pp. 12777–12815, May 2020, doi: 10.1007/s11042-019-08453-9

D. Gede, T. Meranggi, N. Yudistira, and Y. A. Sari, “Batik Classification Using Convolutional Neural Network with Data Improvements,”, Joiv:: Int. J. Inform Visualization,vol 6, no 1,March 2022 6-11. Available:http://joiv.org/index.php/joiv/article/view/716/402

P.S.Hee.Y.J.Seong, "Early Droput Prediction in Online Learning Of University Meachine Learning, Joiv:: Int. J. Inform Visualization, vol 5, no 2, December 2021, 347-353 Available: http://joiv.org/index.php/joiv/article/view/732/375




Refbacks

  • There are currently no refbacks.


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

__________________________________________________________________________
JOIV : International Journal on Informatics Visualization
ISSN 2549-9610  (print) | 2549-9904 (online)
Organized by Department of Information Technology - Politeknik Negeri Padang, and Institute of Visual Informatics - UKM and Soft Computing and Data Mining Centre - UTHM
W : http://joiv.org
E : joiv@pnp.ac.id, hidra@pnp.ac.id, rahmat@pnp.ac.id

View JOIV Stats

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