Expression-Invariant 3D Face Recognition Using K-SVD Method

Maiti, Somsukla; Sangwan, Dhiraj; Raheja, Jagdish Lal

doi:10.1007/978-3-319-04126-1_23

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning algorithms have received increasing attention in the face recognition field, and many researchers discovered the importance of studying 3D face recognition (Maiti, Sangwan & Raheja, 2014;Min et al, 2012;Pabiasz, Starczewski & Marvuglia, 2015;Porro-Munoz et al, 2014;Hu et al, 2017;Sun et al, 2015;Wu, Hou & Zhang, 2017;Tang et al, 2013;Zhang, Zhang & Liu, 2019). On one hand, extracting 3D face information is the key step in 3D face recognition: effective face detection and alignment can increase the overall performance of 3D face recognition, which is critical in both security and commercial 3D face recognition systems.…”

Section: Related Workmentioning

confidence: 99%

3D texture-based face recognition system using fine-tuned deep residual networks

Zheng

Rahmat

Khalid

et al. 2019

PeerJ Computer Science

View full text Add to dashboard Cite

As the technology for 3D photography has developed rapidly in recent years, an enormous amount of 3D images has been produced, one of the directions of research for which is face recognition. Improving the accuracy of a number of data is crucial in 3D face recognition problems. Traditional machine learning methods can be used to recognize 3D faces, but the face recognition rate has declined rapidly with the increasing number of 3D images. As a result, classifying large amounts of 3D image data is time-consuming, expensive, and inefficient. The deep learning methods have become the focus of attention in the 3D face recognition research. In our experiment, the end-to-end face recognition system based on 3D face texture is proposed, combining the geometric invariants, histogram of oriented gradients and the fine-tuned residual neural networks. The research shows that when the performance is evaluated by the FRGC-v2 dataset, as the fine-tuned ResNet deep neural network layers are increased, the best Top-1 accuracy is up to 98.26% and the Top-2 accuracy is 99.40%. The framework proposed costs less iterations than traditional methods. The analysis suggests that a large number of 3D face data by the proposed recognition framework could significantly improve recognition decisions in realistic 3D face scenarios.

show abstract