Multi-feature shape regression for face alignment
Abstract For smart living applications, personal identification as well as behavior and emotion detection becomes more and more important in our daily life. For identity classification and facial expression detection, facial features extracted from face images are the most popular and low-cost infor...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2018-08-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13634-018-0572-6 |
| _version_ | 1818138983423541248 |
|---|---|
| author | Wei-Jong Yang Yi-Chen Chen Pau-Choo Chung Jar-Ferr Yang |
| author_facet | Wei-Jong Yang Yi-Chen Chen Pau-Choo Chung Jar-Ferr Yang |
| author_sort | Wei-Jong Yang |
| collection | DOAJ |
| description | Abstract For smart living applications, personal identification as well as behavior and emotion detection becomes more and more important in our daily life. For identity classification and facial expression detection, facial features extracted from face images are the most popular and low-cost information. The face shape in terms of landmarks estimated by a face alignment method can be used for many applications including virtual face animation and real face classification. In this paper, we propose a robust face alignment method based on the multi-feature shape regression (MSR), which is evolved from the explicit shape regression (ESR) proposed in Cao et al. (Int, Vis, 2014, 107:177–190, Comput). The proposed MSR face alignment method successfully utilizes color, gradient, and regional information to increase accuracy of landmark estimation. For face recognition algorithms, we further suggest a face warping algorithm, which can cooperate with any face alignment algorithm to adjust facial pose variations to improve their recognition performances. For performance evaluations, the proposed and the existing face alignment methods are compared on the face alignment database. Based on alignment-based face recognition concept, the face alignment methods with the proposed face warping method are tested on the face database. Simulation results verify that the proposed MSR face alignment method achieves better performances than the other existing face alignment methods. |
| first_indexed | 2024-12-11T10:20:52Z |
| format | Article |
| id | doaj.art-3e97f35f9bb44c48a5859cb0a04fcd2e |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-12-11T10:20:52Z |
| publishDate | 2018-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-3e97f35f9bb44c48a5859cb0a04fcd2e2022-12-22T01:11:26ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802018-08-012018111310.1186/s13634-018-0572-6Multi-feature shape regression for face alignmentWei-Jong Yang0Yi-Chen Chen1Pau-Choo Chung2Jar-Ferr Yang3Department of Electrical Engineering, Institute of Computer and Communication Engineering, National Cheng Kung UniversityDepartment of Electrical Engineering, Institute of Computer and Communication Engineering, National Cheng Kung UniversityDepartment of Electrical Engineering, Institute of Computer and Communication Engineering, National Cheng Kung UniversityDepartment of Electrical Engineering, Institute of Computer and Communication Engineering, National Cheng Kung UniversityAbstract For smart living applications, personal identification as well as behavior and emotion detection becomes more and more important in our daily life. For identity classification and facial expression detection, facial features extracted from face images are the most popular and low-cost information. The face shape in terms of landmarks estimated by a face alignment method can be used for many applications including virtual face animation and real face classification. In this paper, we propose a robust face alignment method based on the multi-feature shape regression (MSR), which is evolved from the explicit shape regression (ESR) proposed in Cao et al. (Int, Vis, 2014, 107:177–190, Comput). The proposed MSR face alignment method successfully utilizes color, gradient, and regional information to increase accuracy of landmark estimation. For face recognition algorithms, we further suggest a face warping algorithm, which can cooperate with any face alignment algorithm to adjust facial pose variations to improve their recognition performances. For performance evaluations, the proposed and the existing face alignment methods are compared on the face alignment database. Based on alignment-based face recognition concept, the face alignment methods with the proposed face warping method are tested on the face database. Simulation results verify that the proposed MSR face alignment method achieves better performances than the other existing face alignment methods.http://link.springer.com/article/10.1186/s13634-018-0572-6Face alignmentFace warpingFace recognitionPose variationShape regression |
| spellingShingle | Wei-Jong Yang Yi-Chen Chen Pau-Choo Chung Jar-Ferr Yang Multi-feature shape regression for face alignment EURASIP Journal on Advances in Signal Processing Face alignment Face warping Face recognition Pose variation Shape regression |
| title | Multi-feature shape regression for face alignment |
| title_full | Multi-feature shape regression for face alignment |
| title_fullStr | Multi-feature shape regression for face alignment |
| title_full_unstemmed | Multi-feature shape regression for face alignment |
| title_short | Multi-feature shape regression for face alignment |
| title_sort | multi feature shape regression for face alignment |
| topic | Face alignment Face warping Face recognition Pose variation Shape regression |
| url | http://link.springer.com/article/10.1186/s13634-018-0572-6 |
| work_keys_str_mv | AT weijongyang multifeatureshaperegressionforfacealignment AT yichenchen multifeatureshaperegressionforfacealignment AT pauchoochung multifeatureshaperegressionforfacealignment AT jarferryang multifeatureshaperegressionforfacealignment |