Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models
Owing to losing the detailed information, the low‐resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face‐recognition system has been proposed, consisting of the extracted feature vectors from the multiple‐size discrete cosine...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-10-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2012.0211 |
| _version_ | 1827817989900075008 |
|---|---|
| author | Shih‐Ming Huang Yang‐Ting Chou Jar‐Ferr Yang |
| author_facet | Shih‐Ming Huang Yang‐Ting Chou Jar‐Ferr Yang |
| author_sort | Shih‐Ming Huang |
| collection | DOAJ |
| description | Owing to losing the detailed information, the low‐resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face‐recognition system has been proposed, consisting of the extracted feature vectors from the multiple‐size discrete cosine transforms (mDCTs) and the recognition mechanism with selective Gaussian mixture models (sGMMs). The mDCT could extract enough visual features from low‐resolution face images while the sGMM could exclude unreliable observation features in recognition phase. Thus, the mDCT and the sGMM can greatly improve recognition rate at low‐resolution conditions. Experiments are carried out on George Tech and AR facial databases in 16 × 16 and 12 × 12 pixels resolution. The results show that the proposed system achieves better performance than the existing methods for low‐resolution face recognition. |
| first_indexed | 2024-03-12T00:41:30Z |
| format | Article |
| id | doaj.art-b40ce050baab44a590cbce81c7b5705d |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:41:30Z |
| publishDate | 2014-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-b40ce050baab44a590cbce81c7b5705d2023-09-15T07:15:59ZengWileyIET Computer Vision1751-96321751-96402014-10-018538239010.1049/iet-cvi.2012.0211Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture modelsShih‐Ming Huang0Yang‐Ting Chou1Jar‐Ferr Yang2Department of Electrical EngineeringInstitute of Computer and Communication EngineeringNational Cheng Kung UniversityTainanTaiwanDepartment of Electrical EngineeringInstitute of Computer and Communication EngineeringNational Cheng Kung UniversityTainanTaiwanDepartment of Electrical EngineeringInstitute of Computer and Communication EngineeringNational Cheng Kung UniversityTainanTaiwanOwing to losing the detailed information, the low‐resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face‐recognition system has been proposed, consisting of the extracted feature vectors from the multiple‐size discrete cosine transforms (mDCTs) and the recognition mechanism with selective Gaussian mixture models (sGMMs). The mDCT could extract enough visual features from low‐resolution face images while the sGMM could exclude unreliable observation features in recognition phase. Thus, the mDCT and the sGMM can greatly improve recognition rate at low‐resolution conditions. Experiments are carried out on George Tech and AR facial databases in 16 × 16 and 12 × 12 pixels resolution. The results show that the proposed system achieves better performance than the existing methods for low‐resolution face recognition.https://doi.org/10.1049/iet-cvi.2012.0211low-resolution face recognitiondiscrete cosine transformsselective Gaussian mixture modelsrecognition performancefeature vector extractionrecognition phase |
| spellingShingle | Shih‐Ming Huang Yang‐Ting Chou Jar‐Ferr Yang Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models IET Computer Vision low-resolution face recognition discrete cosine transforms selective Gaussian mixture models recognition performance feature vector extraction recognition phase |
| title | Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models |
| title_full | Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models |
| title_fullStr | Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models |
| title_full_unstemmed | Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models |
| title_short | Low‐resolution face recognition in uses of multiple‐size discrete cosine transforms and selective Gaussian mixture models |
| title_sort | low resolution face recognition in uses of multiple size discrete cosine transforms and selective gaussian mixture models |
| topic | low-resolution face recognition discrete cosine transforms selective Gaussian mixture models recognition performance feature vector extraction recognition phase |
| url | https://doi.org/10.1049/iet-cvi.2012.0211 |
| work_keys_str_mv | AT shihminghuang lowresolutionfacerecognitioninusesofmultiplesizediscretecosinetransformsandselectivegaussianmixturemodels AT yangtingchou lowresolutionfacerecognitioninusesofmultiplesizediscretecosinetransformsandselectivegaussianmixturemodels AT jarferryang lowresolutionfacerecognitioninusesofmultiplesizediscretecosinetransformsandselectivegaussianmixturemodels |