Face recognition in video sequence with pose variation using Neural Networks
Keywords:
Pose Invariant Face Recognition, Face Feature Prediction Model (FPM)Abstract
Pose invariant face recognition is still an active challenge in face recognition. Face localization and pose invariant feature detection are the crucial steps in robust pose invariant face recognition. As traditional face detection algorithms like Viola Jones fails to detect face except frontal pose, need of robust algorithms significantly increased. In this paper we are proposing face detection method based on skin color and Earth Movers Distance (EMD) with Particle Swarm Optimization (PSO) for decision making. Pose invariant feature extraction is next challenge and earlier research proved how face alignment degrades quality of face shape and extracted features. This paper proposes Face Feature Prediction Model (FPM) to predict features according to stored face features for min three poses while face registration. Estimated current head pose and current features would be the inputs for FPM. Significant reduction in complexity is possible with use of FPM over traditional face alignment methods. Convolutional Neural Network (CNN) is proposed for accurate face recognition with minor false alarm rate
References
Subramanya Jois, Rakshit Ramesh, Anoop K, “Face Localization using Skin colour and Maximal Entropy based Particle Swarm Optimization for Facial Recognition,” 2017 4th IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics (UPCON) GLA University, Mathura, Oct 26-28, 2017
Changxing Ding, Dacheng Tao, “Trunk-Branch Ensemble Convolutional Neural Network for Video-based Face Recongnition”, 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.
Zhanfu AN, Weigong Deng, Jiani Hu, Yaoyao Zhong, Yuying Zhao, “APA: Adaptive Pose Alignment for Pose-Invariant Face Recognition”, 2019, DOI 10.1109/Access.2019.2894162, IEEE Access
Muhammad Zeeshan Khan, Sadd Harous, Saleet-Ul-Hussan, Muhanmmand Usman Ghani Khan, razi Iqbal, Shahid Mumtaz, “Deep Unified Model for Face Recognition based on Convolution Neural Network and Edge Computing”, 2019, IEEE Access, DOI 10.1109/ACCESS.2019.2918275, IEEE Access.
Gaoli Sang, Jing Li, and Qujun Zhao, “Pose-Invariant Face Recogniton via RGB-D images”, Hindawi Publishing Corporation Computational Intelligence and Neuroscience Volume 2016, Article ID 3563758.
Timothy F. Cootes, Gareth J. Edwards, and Christopher J. Taylor, “Active Appearance Models”, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6 June 2001.
Rabab M. Ramdan and Rehab F. Adbel – Keder, “ Face Recognition Using Particle Swarm Optimization- Based Selected Features”, International Journal of Signal Processing, Image Processing and Pattern Recognition, Vol. 2, No. 2, June 2009.
Ms. Madhavi R. Bichwe, “Face Recognition in Video by Pose variations”, IEEE International Conference on Computer, Communication and Control (IC4-2015).
Sivaram Prasad Mudunuri and Soma Biswas,”Low Resolution Face Recognition Across variations in Pose and Illumination”, IEEE
Transaction on Pattern Analysis and Machine Intelligence, Vol 38. N. 5, May 2016.
Manisha Kasar, Debnath Bhattacharyya and Tai-hoon Kim, “Face Recognition Using Neural Network: A Review”, International Journal of Security and Its applications Vol. 10, No. 3, 2016, pp. 81-100.
