Best Basis Selection Method Using Learning Weights for Face Recognition
In the face recognition field, principal component analysis is essential to the reduction of the image dimension. In spite of frequent use of this analysis, it is commonly believed that the basis faces with large eigenvalues are chosen as the best subset in the nearest neighbor classifiers. We propo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2013-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/13/10/12830 |
| _version_ | 1798042085050286080 |
|---|---|
| author | Wonju Lee Minkyu Cheon Chang-Ho Hyun Mignon Park |
| author_facet | Wonju Lee Minkyu Cheon Chang-Ho Hyun Mignon Park |
| author_sort | Wonju Lee |
| collection | DOAJ |
| description | In the face recognition field, principal component analysis is essential to the reduction of the image dimension. In spite of frequent use of this analysis, it is commonly believed that the basis faces with large eigenvalues are chosen as the best subset in the nearest neighbor classifiers. We propose an alternative that can predict the classification error during the training steps and find the useful basis faces for the similarity metrics of the classical pattern algorithms. In addition, we also show the need for the eye-aligned dataset to have the pure face. The experiments using face images verify that our method reduces the negative effect on the misaligned face images and decreases the weights of the useful basis faces in order to improve the classification accuracy. |
| first_indexed | 2024-04-11T22:30:35Z |
| format | Article |
| id | doaj.art-cfa744a8466f4d36b7c04cc3f911e780 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:30:35Z |
| publishDate | 2013-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cfa744a8466f4d36b7c04cc3f911e7802022-12-22T03:59:26ZengMDPI AGSensors1424-82202013-09-011310128301285110.3390/s131012830Best Basis Selection Method Using Learning Weights for Face RecognitionWonju LeeMinkyu CheonChang-Ho HyunMignon ParkIn the face recognition field, principal component analysis is essential to the reduction of the image dimension. In spite of frequent use of this analysis, it is commonly believed that the basis faces with large eigenvalues are chosen as the best subset in the nearest neighbor classifiers. We propose an alternative that can predict the classification error during the training steps and find the useful basis faces for the similarity metrics of the classical pattern algorithms. In addition, we also show the need for the eye-aligned dataset to have the pure face. The experiments using face images verify that our method reduces the negative effect on the misaligned face images and decreases the weights of the useful basis faces in order to improve the classification accuracy.http://www.mdpi.com/1424-8220/13/10/12830feature selectionsimilarity metricslearning weights |
| spellingShingle | Wonju Lee Minkyu Cheon Chang-Ho Hyun Mignon Park Best Basis Selection Method Using Learning Weights for Face Recognition Sensors feature selection similarity metrics learning weights |
| title | Best Basis Selection Method Using Learning Weights for Face Recognition |
| title_full | Best Basis Selection Method Using Learning Weights for Face Recognition |
| title_fullStr | Best Basis Selection Method Using Learning Weights for Face Recognition |
| title_full_unstemmed | Best Basis Selection Method Using Learning Weights for Face Recognition |
| title_short | Best Basis Selection Method Using Learning Weights for Face Recognition |
| title_sort | best basis selection method using learning weights for face recognition |
| topic | feature selection similarity metrics learning weights |
| url | http://www.mdpi.com/1424-8220/13/10/12830 |
| work_keys_str_mv | AT wonjulee bestbasisselectionmethodusinglearningweightsforfacerecognition AT minkyucheon bestbasisselectionmethodusinglearningweightsforfacerecognition AT changhohyun bestbasisselectionmethodusinglearningweightsforfacerecognition AT mignonpark bestbasisselectionmethodusinglearningweightsforfacerecognition |