A novel weighted fuzzy LDA for face recognition using the genetic algorithm
Fuzzy linear discriminate analysis (FLDA), the principle of which is the remedy of class means via fuzzy optimization, is proven to be an effective feature extraction approach for face recognition. However, some of the between-class distances in the projected space after FLDA may be too small, which...
| Main Authors: | , , |
|---|---|
| Format: | Journal Article |
| Published: |
Springer
2013
|
| Online Access: | http://hdl.handle.net/20.500.11937/17060 |
| _version_ | 1848749355244191744 |
|---|---|
| author | Xue, Mingliang Liu, Wan-Quan Liu, X. |
| author_facet | Xue, Mingliang Liu, Wan-Quan Liu, X. |
| author_sort | Xue, Mingliang |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Fuzzy linear discriminate analysis (FLDA), the principle of which is the remedy of class means via fuzzy optimization, is proven to be an effective feature extraction approach for face recognition. However, some of the between-class distances in the projected space after FLDA may be too small, which can render some classes inseparable. In this paper we propose a weighted FLDA approach that aims to increase the smallest of the between-class distances. This is accomplished by introducing some weighting coefficients to the between-class distances in FLDA. Since the optimal selection of these weighting coefficients is not tractable via standard optimization techniques, the genetic algorithm is adopted as an alternative solution in this paper. The experimental results on some benchmark data sets reveal that the proposed weighted fuzzy LDA can improve the worst recognition rate effectively and also exceed LDA and FLDA’s average performance index. |
| first_indexed | 2025-11-14T07:19:37Z |
| format | Journal Article |
| id | curtin-20.500.11937-17060 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:19:37Z |
| publishDate | 2013 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-170602019-03-08T10:35:03Z A novel weighted fuzzy LDA for face recognition using the genetic algorithm Xue, Mingliang Liu, Wan-Quan Liu, X. Fuzzy linear discriminate analysis (FLDA), the principle of which is the remedy of class means via fuzzy optimization, is proven to be an effective feature extraction approach for face recognition. However, some of the between-class distances in the projected space after FLDA may be too small, which can render some classes inseparable. In this paper we propose a weighted FLDA approach that aims to increase the smallest of the between-class distances. This is accomplished by introducing some weighting coefficients to the between-class distances in FLDA. Since the optimal selection of these weighting coefficients is not tractable via standard optimization techniques, the genetic algorithm is adopted as an alternative solution in this paper. The experimental results on some benchmark data sets reveal that the proposed weighted fuzzy LDA can improve the worst recognition rate effectively and also exceed LDA and FLDA’s average performance index. 2013 Journal Article http://hdl.handle.net/20.500.11937/17060 10.1007/s00521-012-0962-x Springer restricted |
| spellingShingle | Xue, Mingliang Liu, Wan-Quan Liu, X. A novel weighted fuzzy LDA for face recognition using the genetic algorithm |
| title | A novel weighted fuzzy LDA for face recognition using the genetic algorithm |
| title_full | A novel weighted fuzzy LDA for face recognition using the genetic algorithm |
| title_fullStr | A novel weighted fuzzy LDA for face recognition using the genetic algorithm |
| title_full_unstemmed | A novel weighted fuzzy LDA for face recognition using the genetic algorithm |
| title_short | A novel weighted fuzzy LDA for face recognition using the genetic algorithm |
| title_sort | novel weighted fuzzy lda for face recognition using the genetic algorithm |
| url | http://hdl.handle.net/20.500.11937/17060 |