Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition
Face recognition (FR) is one of the most effervescent fields of research with extensive applications that span numerous domains, and it stands resolutely as one of the most challenging problems in computer vision. The accuracy of FR systems is severely affected when two images under consideration fo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-02-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2014.0402 |
| _version_ | 1797684968679276544 |
|---|---|
| author | Vinay. A Vinay S. Shekhar Akshay Kumar C Natarajan. S K.N. Balasubramanya Murthy |
| author_facet | Vinay. A Vinay S. Shekhar Akshay Kumar C Natarajan. S K.N. Balasubramanya Murthy |
| author_sort | Vinay. A |
| collection | DOAJ |
| description | Face recognition (FR) is one of the most effervescent fields of research with extensive applications that span numerous domains, and it stands resolutely as one of the most challenging problems in computer vision. The accuracy of FR systems is severely affected when two images under consideration for a match, vary in their scale and/or affine angles. The prevalent affine and scale invariant recognition systems have been predominantly developed only for objects, and hence in this study, the authors propose a novel approach for faces based on the affine‐SIFT (ASIFT) and two‐dimensional principal component analysis (2DPCA) techniques, to accomplish the formidable task of facial image recognition, invariant of scale and affine angles, i.e. the ability to simulate with enough accuracy, all the distortions caused by the differences in resolution and the variation of the camera optical axis direction. In the formulation of ASIFT‐2DPCA, they investigate three different variants of 2DPCA: classical 2DPCA, quaternion 2DPCA and sparse 2DPCA to gauge as to which is more effective. The authors'experimentations will demonstrate that the proposed approach can robustly handle affine and scale variations, and hence provide better accuracy and matching performance than the state‐of‐the‐art methodologies. |
| first_indexed | 2024-03-12T00:37:35Z |
| format | Article |
| id | doaj.art-cb0872bb11e444f488c41242aa95cfe4 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:37:35Z |
| publishDate | 2016-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-cb0872bb11e444f488c41242aa95cfe42023-09-15T09:27:14ZengWileyIET Computer Vision1751-96321751-96402016-02-01101435910.1049/iet-cvi.2014.0402Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognitionVinay. A0Vinay S. Shekhar1Akshay Kumar C2Natarajan. S3K.N. Balasubramanya Murthy4Computer Science and Engineering DepartmentPES University100 Feet Ring Road, BSK III StageBangalore560085KarnatakaIndiaComputer Science and Engineering DepartmentPES University100 Feet Ring Road, BSK III StageBangalore560085KarnatakaIndiaDepartment of Electronics and Communication EngineeringPES Institute of Technology100 Feet Ring Road, BSK III StageBangalore560085KarnatakaIndiaDepartment of Electronics and Communication EngineeringPES Institute of Technology100 Feet Ring Road, BSK III StageBangalore560085KarnatakaIndiaComputer Science and Engineering DepartmentPES University100 Feet Ring Road, BSK III StageBangalore560085KarnatakaIndiaFace recognition (FR) is one of the most effervescent fields of research with extensive applications that span numerous domains, and it stands resolutely as one of the most challenging problems in computer vision. The accuracy of FR systems is severely affected when two images under consideration for a match, vary in their scale and/or affine angles. The prevalent affine and scale invariant recognition systems have been predominantly developed only for objects, and hence in this study, the authors propose a novel approach for faces based on the affine‐SIFT (ASIFT) and two‐dimensional principal component analysis (2DPCA) techniques, to accomplish the formidable task of facial image recognition, invariant of scale and affine angles, i.e. the ability to simulate with enough accuracy, all the distortions caused by the differences in resolution and the variation of the camera optical axis direction. In the formulation of ASIFT‐2DPCA, they investigate three different variants of 2DPCA: classical 2DPCA, quaternion 2DPCA and sparse 2DPCA to gauge as to which is more effective. The authors'experimentations will demonstrate that the proposed approach can robustly handle affine and scale variations, and hence provide better accuracy and matching performance than the state‐of‐the‐art methodologies.https://doi.org/10.1049/iet-cvi.2014.0402affine-SIFT techniquetwo-dimensional principal component analysisFR systemsaffine and scale invariant recognition systems2DPCA techniquesfacial image recognition |
| spellingShingle | Vinay. A Vinay S. Shekhar Akshay Kumar C Natarajan. S K.N. Balasubramanya Murthy Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition IET Computer Vision affine-SIFT technique two-dimensional principal component analysis FR systems affine and scale invariant recognition systems 2DPCA techniques facial image recognition |
| title | Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition |
| title_full | Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition |
| title_fullStr | Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition |
| title_full_unstemmed | Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition |
| title_short | Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition |
| title_sort | affine scale invariant feature transform and two dimensional principal component analysis a novel framework for affine and scale invariant face recognition |
| topic | affine-SIFT technique two-dimensional principal component analysis FR systems affine and scale invariant recognition systems 2DPCA techniques facial image recognition |
| url | https://doi.org/10.1049/iet-cvi.2014.0402 |
| work_keys_str_mv | AT vinaya affinescaleinvariantfeaturetransformandtwodimensionalprincipalcomponentanalysisanovelframeworkforaffineandscaleinvariantfacerecognition AT vinaysshekhar affinescaleinvariantfeaturetransformandtwodimensionalprincipalcomponentanalysisanovelframeworkforaffineandscaleinvariantfacerecognition AT akshaykumarc affinescaleinvariantfeaturetransformandtwodimensionalprincipalcomponentanalysisanovelframeworkforaffineandscaleinvariantfacerecognition AT natarajans affinescaleinvariantfeaturetransformandtwodimensionalprincipalcomponentanalysisanovelframeworkforaffineandscaleinvariantfacerecognition AT knbalasubramanyamurthy affinescaleinvariantfeaturetransformandtwodimensionalprincipalcomponentanalysisanovelframeworkforaffineandscaleinvariantfacerecognition |