Comparison of Face Detection Methods Under the Influence of Lighting Variation

• Renan Sevilha Sakamoto UFSC
• Benjamin Grando Moreira UFSC
• Pablo Andretta Jaskowiak UFSC

DOI: https://doi.org/10.5753/eniac.2024.245258

Abstract

This article compares facial detection methods under varying lighting conditions, highlighting the impact of illumination on the accuracy of facial recognition algorithms. Different algorithms were analyzed, including Haar-Cascade-based methods, Artificial Neural Network-based methods, and also Histogram of Oriented Gradients. The results indicate that while some methods perform well under varied lighting conditions, others show significant accuracy drops in low-light environments. The research contributes to understanding the limitations and capabilities of facial detection methods under different lighting conditions, making it relevant for the development of more robust systems.

Keywords: facial detection, deep learning, lighting variation

References

Abate, A. et al. (2007). 2d and 3d face recognition: A survey. Pattern Recognition Letters, 28(14):1885–1906.

Behling, A. (2019). Reconhecimento de emoções em vídeo utilizando redes neurais artificiais.

Bradski, G. (2000). The OpenCV Library. Dr. Dobb’s Journal of Software Tools.

Böhm, S. M. (2021). Análise de performance de um algoritmo de reconhecimento facial por visão computacional aplicado a sistemas embarcados.

Dalal, N. e Triggs, B. (2005). Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 1, pages 886–893 vol. 1.

Gamage, C. e Seneviratne, L. (2014). Development of a learning algorithm for facial recognition under varying illumination. In: Proceedings of the 7th internacional conference on information and automation for sustainability. 1(7):1–6.

Georghiades, A., Belhumeur, P., e Kriegman, D. (2001). From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(6):643–660.

Jain, A., Hong, L., e Pankanti, S. (2000). Biometric identification. Communications of the ACM, 43(2):90–98.

Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., e Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093.

Kaur, S. e Sharma, D. (2023). Comparative study of face detection using cascaded haar, hog and mtcnn algorithms. In 2023 3rd International Conference on Advancement in Electronics & Communication Engineering (AECE), pages 536–541.

King, D. E. (2009). Dlib-ml: A machine learning toolkit. Journal of Machine Learning Research, 10:1755–1758.

Kumar, A., Kaur, A., e Kumar, M. (2019). Face detection techniques: a review. Artificial Intelligence Review, 52(2):927–948.

LeCun, Y., Bengio, Y., e Hinton, G. (2015). Deep learning. 521(7553):436–444.

Lee, H.-W., Peng, F.-F., Lee, X.-Y., Dai, H.-N., e Zhu, Y. (2018). Research on face detection under different lighting. In 2018 IEEE International Conference on Applied System Invention (ICASI), pages 1145–1148.

Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L., e Dollár, P. (2015). Microsoft coco: Common objects in context.

Muller, A. C. e Guido, S. (2016). Introduction to machine learning with Python. O’Reilly, Gravenstein Highway North, Sebastopol.

Ochoa-Villegas, M. A., Nolazco-Flores, J. A., Barron-Cano, O., e Kakadiaris, I. A. (2015). Addressing the illumination challenge in two-dimensional face recognition: a survey. IET Computer Vision, 9(6):978–992.

Pankanti, S., Bolle, R. M., e Jain, A. (2000). Biometrics: The future of identification [guest eeditors’ introduction]. Computer, 33(2):46–49.

Rana, W., Pandey, R., e Kaur, J. (2022). Face recognition in different light conditions. In Smys, S., Balas, V. E., e Palanisamy, R., editors, Inventive Computation and Information Technologies, pages 839–850, Singapore. Springer Nature Singapore.

Redmon, J., Divvala, S., Girshick, R., e Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788.

Viola, P. e Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, volume 1, pages I–I.

Zafeiriou, S., Zhang, C., e Zhang, Z. (2015). A survey on face detection in the wild: Past, present and future. Computer Vision and Image Understanding, 138:1–24.

Zhang, K., Zhang, Z., Li, Z., e Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE signal processing letters, 23(10):1499–1503.

Zhang, L., Wang, H., e Chen, Z. (2021). A multi-task cascaded algorithm with optimized convolution neural network for face detection. In 2021 Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS), pages 242–245.