PERBANDINGAN DTCWT DAN NM F PADA FACE RECOGNITION MENGGUNAKAN EUCLIDEAN DISTANCE
| Main Authors: | David, David, Ariandy Luwinda, Ferdinand |
|---|---|
| Format: | Article PeerReviewed |
| Terbitan: |
Binus University
, 2014
|
| Online Access: |
http://eprints.binus.ac.id/31594/ http://library.binus.ac.id/Collections/journal_detail.aspx?subject=25&volnoed=Volume 05 / Nomor 01 / June 2014&title=PERBANDINGAN DTCWT DAN NM F PADA FACE RECOGNITION MENGGUNAKAN EUCLIDEAN DISTANCE |
Daftar Isi:
- Dual tree complex wavelet transform (DTCWT) is<br/>widely used for representation of face image<br/>features. DTCWT is more frequently used than Gabor or Discrete Wavelet Transform (DWT) because it provides<br/>good directional selectivity in six different directions<br/>. Meanwhile, non-negative matrix factorization (NMF) is<br/>also frequently used since it can reduce high dimensi<br/>onal feature into smaller one<br/>without losing important<br/>features. This research focused on comparison betw<br/>een DTCWT and NMF as feature extraction and Euclidean<br/>Distance for classification. This research used ORL<br/>Faces database. Experimental<br/>result showed that NMF<br/>provided better results than DTCWT did. NMF reached 92% of accuracy and DTCWT reached 78% of<br/>accuracy.