Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction
Facial Beauty Prediction (FBP) is an important visual recognition problem to evaluate the attractiveness of faces according to human perception. Most existing FBP methods are based on supervised solutions using geometric or deep features. Semi-supervised learning for FBP is an almost unexplored rese...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/15/6/207 |
| _version_ | 1797490842261258240 |
|---|---|
| author | Fadi Dornaika Abdelmalik Moujahid |
| author_facet | Fadi Dornaika Abdelmalik Moujahid |
| author_sort | Fadi Dornaika |
| collection | DOAJ |
| description | Facial Beauty Prediction (FBP) is an important visual recognition problem to evaluate the attractiveness of faces according to human perception. Most existing FBP methods are based on supervised solutions using geometric or deep features. Semi-supervised learning for FBP is an almost unexplored research area. In this work, we propose a graph-based semi-supervised method in which multiple graphs are constructed to find the appropriate graph representation of the face images (with and without scores). The proposed method combines both geometric and deep feature-based graphs to produce a high-level representation of face images instead of using a single face descriptor and also improves the discriminative ability of graph-based score propagation methods. In addition to the data graph, our proposed approach fuses an additional graph adaptively built on the predicted beauty values. Experimental results on the SCUTFBP-5500 facial beauty dataset demonstrate the superiority of the proposed algorithm compared to other state-of-the-art methods. |
| first_indexed | 2024-03-10T00:38:51Z |
| format | Article |
| id | doaj.art-f5ea1777d3aa431d8283eb1e05464cae |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T00:38:51Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-f5ea1777d3aa431d8283eb1e05464cae2023-11-23T15:13:19ZengMDPI AGAlgorithms1999-48932022-06-0115620710.3390/a15060207Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty PredictionFadi Dornaika0Abdelmalik Moujahid1Henan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng 475001, ChinaDepartment of Computer Science and Artificial Intelligence, Faculty of Computer Science, University of the Basque Country UPV/EHU, M. Lardizabal 1, 20018 Donostia-San Sebastián, SpainFacial Beauty Prediction (FBP) is an important visual recognition problem to evaluate the attractiveness of faces according to human perception. Most existing FBP methods are based on supervised solutions using geometric or deep features. Semi-supervised learning for FBP is an almost unexplored research area. In this work, we propose a graph-based semi-supervised method in which multiple graphs are constructed to find the appropriate graph representation of the face images (with and without scores). The proposed method combines both geometric and deep feature-based graphs to produce a high-level representation of face images instead of using a single face descriptor and also improves the discriminative ability of graph-based score propagation methods. In addition to the data graph, our proposed approach fuses an additional graph adaptively built on the predicted beauty values. Experimental results on the SCUTFBP-5500 facial beauty dataset demonstrate the superiority of the proposed algorithm compared to other state-of-the-art methods.https://www.mdpi.com/1999-4893/15/6/207face beauty predictiongraph-based semi-supervised learninggraph fusionscore propagationlabel graphflexible manifold embedding |
| spellingShingle | Fadi Dornaika Abdelmalik Moujahid Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction Algorithms face beauty prediction graph-based semi-supervised learning graph fusion score propagation label graph flexible manifold embedding |
| title | Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction |
| title_full | Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction |
| title_fullStr | Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction |
| title_full_unstemmed | Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction |
| title_short | Multi-View Graph Fusion for Semi-Supervised Learning: Application to Image-Based Face Beauty Prediction |
| title_sort | multi view graph fusion for semi supervised learning application to image based face beauty prediction |
| topic | face beauty prediction graph-based semi-supervised learning graph fusion score propagation label graph flexible manifold embedding |
| url | https://www.mdpi.com/1999-4893/15/6/207 |
| work_keys_str_mv | AT fadidornaika multiviewgraphfusionforsemisupervisedlearningapplicationtoimagebasedfacebeautyprediction AT abdelmalikmoujahid multiviewgraphfusionforsemisupervisedlearningapplicationtoimagebasedfacebeautyprediction |