Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions
The scale invariant feature transform (SIFT), which was proposed by David Lowe, is a powerful method that extracts and describes local features called keypoints from images. These keypoints are invariant to scale, translation, and rotation, and partially invariant to image illumination variation. De...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-08-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2017.0190 |
| _version_ | 1797684789555232768 |
|---|---|
| author | Meriama Mahamdioua Mohamed Benmohammed |
| author_facet | Meriama Mahamdioua Mohamed Benmohammed |
| author_sort | Meriama Mahamdioua |
| collection | DOAJ |
| description | The scale invariant feature transform (SIFT), which was proposed by David Lowe, is a powerful method that extracts and describes local features called keypoints from images. These keypoints are invariant to scale, translation, and rotation, and partially invariant to image illumination variation. Despite their robustness against these variations, strong lighting variation is a difficult challenge for SIFT‐based facial recognition systems, where significant degradation of performance has been reported. To develop a robust system under these conditions, variation in lighting must be first eliminated. Additionally, SIFT parameter default values that remove unstable keypoints and inadequately matched keypoints are not well‐suited to images with illumination variation. SIFT keypoints can also be incorrectly matched when using the original SIFT matching method. To overcome this issue, the authors propose propose a method for removing the illumination variation in images and correctly setting SIFT's main parameter values (contrast threshold, curvature threshold, and match threshold) to enhance SIFT feature extraction and matching. The proposed method is based on an estimation of comparative image lighting quality, which is evaluated through an automatic estimation of gamma correction value. Through facial recognition experiments, the authors find significant results that clearly illustrate the importance of the proposed robust recognition system. |
| first_indexed | 2024-03-12T00:34:52Z |
| format | Article |
| id | doaj.art-2211052939ec4c6a85be94febc556fa6 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:34:52Z |
| publishDate | 2018-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-2211052939ec4c6a85be94febc556fa62023-09-15T09:48:11ZengWileyIET Computer Vision1751-96321751-96402018-08-0112562363310.1049/iet-cvi.2017.0190Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditionsMeriama Mahamdioua0Mohamed Benmohammed1TLSI DepartmentNTIC Faculty, University of Constantine 2ConstantineAlgeriaLIRE Laboratory, University of Constantine 2ConstantineAlgeriaThe scale invariant feature transform (SIFT), which was proposed by David Lowe, is a powerful method that extracts and describes local features called keypoints from images. These keypoints are invariant to scale, translation, and rotation, and partially invariant to image illumination variation. Despite their robustness against these variations, strong lighting variation is a difficult challenge for SIFT‐based facial recognition systems, where significant degradation of performance has been reported. To develop a robust system under these conditions, variation in lighting must be first eliminated. Additionally, SIFT parameter default values that remove unstable keypoints and inadequately matched keypoints are not well‐suited to images with illumination variation. SIFT keypoints can also be incorrectly matched when using the original SIFT matching method. To overcome this issue, the authors propose propose a method for removing the illumination variation in images and correctly setting SIFT's main parameter values (contrast threshold, curvature threshold, and match threshold) to enhance SIFT feature extraction and matching. The proposed method is based on an estimation of comparative image lighting quality, which is evaluated through an automatic estimation of gamma correction value. Through facial recognition experiments, the authors find significant results that clearly illustrate the importance of the proposed robust recognition system.https://doi.org/10.1049/iet-cvi.2017.0190SIFT automatic adaptationrobust facial recognitionuncontrolled lighting conditionsscale invariant feature transformlocal feature extractionimage illumination variation |
| spellingShingle | Meriama Mahamdioua Mohamed Benmohammed Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions IET Computer Vision SIFT automatic adaptation robust facial recognition uncontrolled lighting conditions scale invariant feature transform local feature extraction image illumination variation |
| title | Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions |
| title_full | Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions |
| title_fullStr | Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions |
| title_full_unstemmed | Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions |
| title_short | Automatic adaptation of SIFT for robust facial recognition in uncontrolled lighting conditions |
| title_sort | automatic adaptation of sift for robust facial recognition in uncontrolled lighting conditions |
| topic | SIFT automatic adaptation robust facial recognition uncontrolled lighting conditions scale invariant feature transform local feature extraction image illumination variation |
| url | https://doi.org/10.1049/iet-cvi.2017.0190 |
| work_keys_str_mv | AT meriamamahamdioua automaticadaptationofsiftforrobustfacialrecognitioninuncontrolledlightingconditions AT mohamedbenmohammed automaticadaptationofsiftforrobustfacialrecognitioninuncontrolledlightingconditions |