Histogram of gradient phases: a new local descriptor for face recognition
Gradient‐based local descriptors have received more attention these years and have been successfully used in many applications such as human detection and face recognition. The advantages of the local descriptors are the resistance to the local geometric and photometric errors and the robustness to...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-12-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2013.0208 |
| _version_ | 1797684529252532224 |
|---|---|
| author | Ching‐Yao Su Jar‐Ferr Yang |
| author_facet | Ching‐Yao Su Jar‐Ferr Yang |
| author_sort | Ching‐Yao Su |
| collection | DOAJ |
| description | Gradient‐based local descriptors have received more attention these years and have been successfully used in many applications such as human detection and face recognition. The advantages of the local descriptors are the resistance to the local geometric and photometric errors and the robustness to the expression variations. In this paper, the authors propose a new local descriptor called the histogram of gradient phases (HGP), which has some intriguing properties compared with the existing local descriptors such as the histogram of orientated gradients and DAISY for face recognition under the unconstrained conditions. In contrast with the histogram of the oriented gradient descriptor, the orientation histogram is computed from the estimated gradient phase distributions instead of weighting the votes of the gradient magnitudes. In this paper, the phase distributions are estimated by means of the gradient phases and the variances are decided by the estimated gradient signal‐to‐noise ratios of the pixels in a local region. The HGP descriptor which takes the confidence of the gradient phase into account is more discriminative and less sensitive to the normalisation process than most local descriptors, which significantly degrade without a proper normalisation. The simulation results show that the proposed HGP descriptor achieves a better performance and is more robust than the existing local descriptors. |
| first_indexed | 2024-03-12T00:31:00Z |
| format | Article |
| id | doaj.art-2de63ae6864143b89544531156dd4435 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:31:00Z |
| publishDate | 2014-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-2de63ae6864143b89544531156dd44352023-09-15T10:15:58ZengWileyIET Computer Vision1751-96321751-96402014-12-018655656710.1049/iet-cvi.2013.0208Histogram of gradient phases: a new local descriptor for face recognitionChing‐Yao Su0Jar‐Ferr Yang1Advanced Optoelectric Technology CenterInstitute of Computer and Communication EngineeringDepartment of Electrical EngineeringNational Cheng Kung UniversityTainanTaiwanAdvanced Optoelectric Technology CenterInstitute of Computer and Communication EngineeringDepartment of Electrical EngineeringNational Cheng Kung UniversityTainanTaiwanGradient‐based local descriptors have received more attention these years and have been successfully used in many applications such as human detection and face recognition. The advantages of the local descriptors are the resistance to the local geometric and photometric errors and the robustness to the expression variations. In this paper, the authors propose a new local descriptor called the histogram of gradient phases (HGP), which has some intriguing properties compared with the existing local descriptors such as the histogram of orientated gradients and DAISY for face recognition under the unconstrained conditions. In contrast with the histogram of the oriented gradient descriptor, the orientation histogram is computed from the estimated gradient phase distributions instead of weighting the votes of the gradient magnitudes. In this paper, the phase distributions are estimated by means of the gradient phases and the variances are decided by the estimated gradient signal‐to‐noise ratios of the pixels in a local region. The HGP descriptor which takes the confidence of the gradient phase into account is more discriminative and less sensitive to the normalisation process than most local descriptors, which significantly degrade without a proper normalisation. The simulation results show that the proposed HGP descriptor achieves a better performance and is more robust than the existing local descriptors.https://doi.org/10.1049/iet-cvi.2013.0208gradient phase histogramface recognitiongradient based local descriptorslocal geometric errorphotometric errorexpression variations |
| spellingShingle | Ching‐Yao Su Jar‐Ferr Yang Histogram of gradient phases: a new local descriptor for face recognition IET Computer Vision gradient phase histogram face recognition gradient based local descriptors local geometric error photometric error expression variations |
| title | Histogram of gradient phases: a new local descriptor for face recognition |
| title_full | Histogram of gradient phases: a new local descriptor for face recognition |
| title_fullStr | Histogram of gradient phases: a new local descriptor for face recognition |
| title_full_unstemmed | Histogram of gradient phases: a new local descriptor for face recognition |
| title_short | Histogram of gradient phases: a new local descriptor for face recognition |
| title_sort | histogram of gradient phases a new local descriptor for face recognition |
| topic | gradient phase histogram face recognition gradient based local descriptors local geometric error photometric error expression variations |
| url | https://doi.org/10.1049/iet-cvi.2013.0208 |
| work_keys_str_mv | AT chingyaosu histogramofgradientphasesanewlocaldescriptorforfacerecognition AT jarferryang histogramofgradientphasesanewlocaldescriptorforfacerecognition |