Feature Fusion and NRML Metric Learning for Facial Kinship Verification
Features extracted from facial images are used in various fields such as kinship verification. The kinship verification system determines the kin or non-kin relation between a pair of facial images by analysing their facial features. In this research, different texture and color features have been u...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Graz University of Technology
2023-04-01
|
| Series: | Journal of Universal Computer Science |
| Subjects: | |
| Online Access: | https://lib.jucs.org/article/89254/download/pdf/ |
| _version_ | 1797836710264963072 |
|---|---|
| author | Fahimeh Ramazankhani Mahdi Yazdian-Dehkord Mehdi Rezaeian |
| author_facet | Fahimeh Ramazankhani Mahdi Yazdian-Dehkord Mehdi Rezaeian |
| author_sort | Fahimeh Ramazankhani |
| collection | DOAJ |
| description | Features extracted from facial images are used in various fields such as kinship verification. The kinship verification system determines the kin or non-kin relation between a pair of facial images by analysing their facial features. In this research, different texture and color features have been used along with the metric learning method, to verify the kinship for the four kinship relations of father-son, father-daughter, mother-son and mother-daughter. First, by fusing effective features, NRML metric learning used to generate the discriminative feature vector, then SVM classifier used to verify to kinship relations. To measure the accuracy of the proposed method, KinFaceW-I and KinFaceW-II databases have been used. The results of the evaluations show that the feature fusion and NRML metric learning methods have been able to improve the performance of the kinship verification system. In addition to the proposed approach, the effect of feature extraction from the image blocks or the whole image is investigated and the results are presented. The results indicate that feature extraction in block form, can be effective in improving the final accuracy of kinship verification. |
| first_indexed | 2024-04-09T15:14:23Z |
| format | Article |
| id | doaj.art-d2156c97d5ee4c7bb6c8f42f2bfba7dd |
| institution | Directory Open Access Journal |
| issn | 0948-6968 |
| language | English |
| last_indexed | 2024-04-09T15:14:23Z |
| publishDate | 2023-04-01 |
| publisher | Graz University of Technology |
| record_format | Article |
| series | Journal of Universal Computer Science |
| spelling | doaj.art-d2156c97d5ee4c7bb6c8f42f2bfba7dd2023-04-30T08:11:08ZengGraz University of TechnologyJournal of Universal Computer Science0948-69682023-04-0129432634810.3897/jucs.8925489254Feature Fusion and NRML Metric Learning for Facial Kinship VerificationFahimeh Ramazankhani0Mahdi Yazdian-Dehkord1Mehdi Rezaeian2Yazd UniversityYazd UniversityYazd UniversityFeatures extracted from facial images are used in various fields such as kinship verification. The kinship verification system determines the kin or non-kin relation between a pair of facial images by analysing their facial features. In this research, different texture and color features have been used along with the metric learning method, to verify the kinship for the four kinship relations of father-son, father-daughter, mother-son and mother-daughter. First, by fusing effective features, NRML metric learning used to generate the discriminative feature vector, then SVM classifier used to verify to kinship relations. To measure the accuracy of the proposed method, KinFaceW-I and KinFaceW-II databases have been used. The results of the evaluations show that the feature fusion and NRML metric learning methods have been able to improve the performance of the kinship verification system. In addition to the proposed approach, the effect of feature extraction from the image blocks or the whole image is investigated and the results are presented. The results indicate that feature extraction in block form, can be effective in improving the final accuracy of kinship verification.https://lib.jucs.org/article/89254/download/pdf/kinship verificationfeature fusionmetric learn |
| spellingShingle | Fahimeh Ramazankhani Mahdi Yazdian-Dehkord Mehdi Rezaeian Feature Fusion and NRML Metric Learning for Facial Kinship Verification Journal of Universal Computer Science kinship verification feature fusion metric learn |
| title | Feature Fusion and NRML Metric Learning for Facial Kinship Verification |
| title_full | Feature Fusion and NRML Metric Learning for Facial Kinship Verification |
| title_fullStr | Feature Fusion and NRML Metric Learning for Facial Kinship Verification |
| title_full_unstemmed | Feature Fusion and NRML Metric Learning for Facial Kinship Verification |
| title_short | Feature Fusion and NRML Metric Learning for Facial Kinship Verification |
| title_sort | feature fusion and nrml metric learning for facial kinship verification |
| topic | kinship verification feature fusion metric learn |
| url | https://lib.jucs.org/article/89254/download/pdf/ |
| work_keys_str_mv | AT fahimehramazankhani featurefusionandnrmlmetriclearningforfacialkinshipverification AT mahdiyazdiandehkord featurefusionandnrmlmetriclearningforfacialkinshipverification AT mehdirezaeian featurefusionandnrmlmetriclearningforfacialkinshipverification |