Robust face recognition for occluded real‐world images using constrained probabilistic sparse network
Abstract Aiming at the occluded real‐world face images across illumination, pose, expression, and resolution variations, a robust face recognition for occluded real‐world images using constrained probabilistic sparse network is presented. A constrained probabilistic sparse representation network is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-04-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12414 |
| _version_ | 1819294602463543296 |
|---|---|
| author | Xiang Ma Qinqin Ma Qian Ma Xiao Han |
| author_facet | Xiang Ma Qinqin Ma Qian Ma Xiao Han |
| author_sort | Xiang Ma |
| collection | DOAJ |
| description | Abstract Aiming at the occluded real‐world face images across illumination, pose, expression, and resolution variations, a robust face recognition for occluded real‐world images using constrained probabilistic sparse network is presented. A constrained probabilistic sparse representation network is constructed to obtain the features of all the training images from a global perspective, and the new network nodes are generated through the random combination of the training images. In the probabilistic sparse representation network, the probabilities of each class of the sparse subspace that the occluded test images individually belong to are defined and calculated. The final classifications of the test images are determined by the joint maximum probability of the network nodes. Meanwhile the second‐order gradient constraint is the first introduced in the probabilistic sparse representation network. It is found that the constraint uses the adjacent pixels of the face images to obtain the local texture similarity, and further use the local texture similarity to distinguish the occlusion and non‐occlusion parts. Thus the constraint can reduce the influence of the occlusion part on face recognition. Extensive experiments with the 12 existing methods on the five face databases demonstrate that the recognition rate of the proposed method is the best than the non‐deep learning methods compared, and the proposed method can obtain nearly the same recognition rate with an advantage of a very less time consumption compared to the state‐of‐the‐art deep learning methods. |
| first_indexed | 2024-12-24T04:28:56Z |
| format | Article |
| id | doaj.art-639627deea0e4d73a575f7edda1bffe4 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-12-24T04:28:56Z |
| publishDate | 2022-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-639627deea0e4d73a575f7edda1bffe42022-12-21T17:15:29ZengWileyIET Image Processing1751-96591751-96672022-04-011651359137510.1049/ipr2.12414Robust face recognition for occluded real‐world images using constrained probabilistic sparse networkXiang Ma0Qinqin Ma1Qian Ma2Xiao Han3School of Information Engineering Chang'an University Xi'an 710048 ChinaSchool of Information Engineering Chang'an University Xi'an 710048 ChinaSchool of Information Engineering Chang'an University Xi'an 710048 ChinaSchool of Information Engineering Chang'an University Xi'an 710048 ChinaAbstract Aiming at the occluded real‐world face images across illumination, pose, expression, and resolution variations, a robust face recognition for occluded real‐world images using constrained probabilistic sparse network is presented. A constrained probabilistic sparse representation network is constructed to obtain the features of all the training images from a global perspective, and the new network nodes are generated through the random combination of the training images. In the probabilistic sparse representation network, the probabilities of each class of the sparse subspace that the occluded test images individually belong to are defined and calculated. The final classifications of the test images are determined by the joint maximum probability of the network nodes. Meanwhile the second‐order gradient constraint is the first introduced in the probabilistic sparse representation network. It is found that the constraint uses the adjacent pixels of the face images to obtain the local texture similarity, and further use the local texture similarity to distinguish the occlusion and non‐occlusion parts. Thus the constraint can reduce the influence of the occlusion part on face recognition. Extensive experiments with the 12 existing methods on the five face databases demonstrate that the recognition rate of the proposed method is the best than the non‐deep learning methods compared, and the proposed method can obtain nearly the same recognition rate with an advantage of a very less time consumption compared to the state‐of‐the‐art deep learning methods.https://doi.org/10.1049/ipr2.12414 |
| spellingShingle | Xiang Ma Qinqin Ma Qian Ma Xiao Han Robust face recognition for occluded real‐world images using constrained probabilistic sparse network IET Image Processing |
| title | Robust face recognition for occluded real‐world images using constrained probabilistic sparse network |
| title_full | Robust face recognition for occluded real‐world images using constrained probabilistic sparse network |
| title_fullStr | Robust face recognition for occluded real‐world images using constrained probabilistic sparse network |
| title_full_unstemmed | Robust face recognition for occluded real‐world images using constrained probabilistic sparse network |
| title_short | Robust face recognition for occluded real‐world images using constrained probabilistic sparse network |
| title_sort | robust face recognition for occluded real world images using constrained probabilistic sparse network |
| url | https://doi.org/10.1049/ipr2.12414 |
| work_keys_str_mv | AT xiangma robustfacerecognitionforoccludedrealworldimagesusingconstrainedprobabilisticsparsenetwork AT qinqinma robustfacerecognitionforoccludedrealworldimagesusingconstrainedprobabilisticsparsenetwork AT qianma robustfacerecognitionforoccludedrealworldimagesusingconstrainedprobabilisticsparsenetwork AT xiaohan robustfacerecognitionforoccludedrealworldimagesusingconstrainedprobabilisticsparsenetwork |