scholarly journals A Multi-Stage Classifier for Face Recognition Undertaken by Coarse-to-fine Strategy

10.5772/6639 ◽  
2009 ◽  
Author(s):  
Jiann-Der Lee ◽  
Chen-Hui Kuo
Keyword(s):  
Face Recognition ◽  
Multi Stage ◽  
Coarse To Fine

Robust coarse-to-fine face recognition method

Optik ◽  
2015 ◽  
Vol 126 (23) ◽  
pp. 4159-4165
Author(s):  
Qingxiang Feng ◽  
Qi Zhu ◽  
Lin-Lin Tang ◽  
Jeng-Shyang Pan
Keyword(s):  
Face Recognition ◽  
Recognition Method ◽  
Coarse To Fine

Multi-stage face recognition for biometric access

2015 ◽  
Author(s):  
Ashutosh Mishra ◽  
Kishan Kumar ◽  
Shyam Nandan Rai ◽  
V. K. Mittal
Keyword(s):  
Face Recognition ◽  
Multi Stage

scholarly journals Detailed 3D human body reconstruction from multi-view images combining voxel super-resolution and learned implicit representation

2021 ◽  
Author(s):  
Zhongguo Li ◽  
Magnus Oskarsson ◽  
Anders Heyden
Keyword(s):  
Human Body ◽  
Super Resolution ◽  
3D Models ◽  
Implicit Function ◽  
Implicit Representation ◽  
Multi Scale ◽  
Multi Stage ◽  
Synthetic Datasets ◽  
Human Body Models ◽  
Coarse To Fine

AbstractThe task of reconstructing detailed 3D human body models from images is interesting but challenging in computer vision due to the high freedom of human bodies. This work proposes a coarse-to-fine method to reconstruct detailed 3D human body from multi-view images combining Voxel Super-Resolution (VSR) based on learning the implicit representation. Firstly, the coarse 3D models are estimated by learning an Pixel-aligned Implicit Function based on Multi-scale Features (MF-PIFu) which are extracted by multi-stage hourglass networks from the multi-view images. Then, taking the low resolution voxel grids which are generated by the coarse 3D models as input, the VSR is implemented by learning an implicit function through a multi-stage 3D convolutional neural network. Finally, the refined detailed 3D human body models can be produced by VSR which can preserve the details and reduce the false reconstruction of the coarse 3D models. Benefiting from the implicit representation, the training process in our method is memory efficient and the detailed 3D human body produced by our method from multi-view images is the continuous decision boundary with high-resolution geometry. In addition, the coarse-to-fine method based on MF-PIFu and VSR can remove false reconstructions and preserve the appearance details in the final reconstruction, simultaneously. In the experiments, our method quantitatively and qualitatively achieves the competitive 3D human body models from images with various poses and shapes on both the real and synthetic datasets.

Boosting non-graph matching feature-based face recognition with a multi-stage matching strategy

2017 ◽  
Vol 15 (02) ◽  
pp. 1750017 ◽  
Author(s):  
Xianming Chen ◽  
Chaoyang Zhang ◽  
Zhaoxian Zhou
Keyword(s):  
Face Recognition ◽  
Graph Matching ◽  
Divide And Conquer ◽  
Experimental Result ◽  
Multi Stage ◽  
Recognition Result ◽  
Feature Based ◽  
Matching Strategy ◽  
Stage Matching ◽  
Global And Local

In this paper, a multi-stage matching strategy is proposed to boost the performance of a non-graph matching feature-based face recognition. As the gallery size increases, the problem of recognition degradation gradually arises, due to the fact that the correct matching of feature points becomes more and more difficult. Other than only one round of matching in traditional methods, the multi-stage matching strategy determines the recognition result step by step. Instead of finding the best one matching, each step picks out a small portion of the training candidates and removes the others. The behavior of picking and removing repeats until the number of remaining candidates is small enough to produce the final result. Two multi-stage matching algorithms, n-ary elimination and divide and conquer, are introduced into the non-graph matching feature-based method from the perspectives of global and local, respectively. The experimental result shows that with the multi-stage matching strategy, the recognition accuracy of the non-graph matching feature-based method is evidently boosted. Moreover, the improvement level also increases with the gallery size.

Sign in / Sign up

Export Citation Format

Share Document