Abstract
Face recognition has received significant attention because of its numerous applications in access control, security, and surveillance system. In real-world scenarios, uncontrollable lighting conditions, a variety of posture and facial expressions, and noisy facial images can degrade the face recognition accuracy. Hence, the research based on the HOG algorithm and pre-processing implementation framework processing framework to improve face recognition accuracy is proposed. This proposal consists of four stages where the first stage is to build a dataset of 15 subjects and has five series of multi-poses of facial images. The second stage is focused on enhancing the pre-processing framework that consists of denoising colored, illumination normalization, and facial alignment algorithms. For the third stage, the HOG algorithm is utilized as a feature descriptor to detect the face. The fourth stage is implementing the deep convolution neural network to evaluate the accuracy of face recognition. From the observation, the improvement in the accuracy rate is up by 4.37% after the enhancement of the pre-processing framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Transparency Market Research: Facial Recognition Market, 24 May 2018. https://www.transparencymarketresearch.com/facial-recognition-market.html. Accessed 1 Jan 2020
George, D.: HOG based face detection in live video streaming. Int. J. Comput. Sci. Technol. Res. 10, 195–202 (2016)
Rekha, N., Kurian, M.Z.: Face detection in real-time based on HOG. Int. J. Adv. Res. Comput. Eng. Technol. (IJARCET) 3, 1345–1352 (2014)
Chude-Olisah, C.C., Sulong, G., Chude-Okonkwo, U.A.K., Hashim, S.Z.M.: Illumination normalization for edge-based face recognition using the fusion of RGB normalization and gamma correction. In: 2013 IEEE International Conference on Signal and Image Processing Applications, Melaka, Malaysia (2013)
Bharadwaj, S., Bhatt, H., Vatsa, M., Singh, R., Noore, A.: Quality assessment based denoising to improve face recognition performance. In: IEEE CVPR 2011 Workshops, Colorado Spring, CO, USA (2011)
Zhong, Y., Chen, J., Huang, B.: Toward end-to-end face recognition through alignment learning. IEEE Signal Process. Lett. 24, 1214–1216 (2017)
Mohamed, A., Ab Wahab, M.N., Suhaily, S., Arasu, D.: Smart mirror design powered by raspberry pi. In: Proceedings of the 2018 Artificial Intelligence and Cloud Computing Conference, pp. 166–173 (2018)
Acknowledgements
This research collaborates between the Robotics, Computer Vision & Image Processing (RCVIP) Research Group Lab at the School of Computer Sciences, Universiti Sains Malaysia (USM) and Intel Technology Sdn. Bhd., Penang. This project was supported by USM Short Term Grant (PKOMP/6315262).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Seng, Y.W., Wahab, M.N.A., Chuan, W.C., Wen, K.Y.K., Lun, L.T. (2022). Enhanced the Face Recognition Accuracy by Using Histogram of Oriented Gradients (HOG) in Pre-processing Approach. In: Mahyuddin, N.M., Mat Noor, N.R., Mat Sakim, H.A. (eds) Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications. Lecture Notes in Electrical Engineering, vol 829. Springer, Singapore. https://doi.org/10.1007/978-981-16-8129-5_6
Download citation
DOI: https://doi.org/10.1007/978-981-16-8129-5_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8128-8
Online ISBN: 978-981-16-8129-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)