Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network
A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied as the classifier for face detection. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm that grows dynamically during training a...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
2009
|
| Online Access: | http://hdl.handle.net/20.500.11937/42759 |
| _version_ | 1848756507548581888 |
|---|---|
| author | Yeong, L. Ang, L. Lim, Hann Seng, K. |
| author_facet | Yeong, L. Ang, L. Lim, Hann Seng, K. |
| author_sort | Yeong, L. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied as the classifier for face detection. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm that grows dynamically during training allowing subclasses in the training data to be learnt. The network is trained using a reduced dimensionality categorized wavelet coefficients of the image data. Experimental results obtained show that a 94% correct detection rate can be achieved with less than 6% false positives. © 2009 World Scientific Publishing Company. |
| first_indexed | 2025-11-14T09:13:18Z |
| format | Journal Article |
| id | curtin-20.500.11937-42759 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T09:13:18Z |
| publishDate | 2009 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-427592017-09-13T14:29:24Z Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network Yeong, L. Ang, L. Lim, Hann Seng, K. A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied as the classifier for face detection. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm that grows dynamically during training allowing subclasses in the training data to be learnt. The network is trained using a reduced dimensionality categorized wavelet coefficients of the image data. Experimental results obtained show that a 94% correct detection rate can be achieved with less than 6% false positives. © 2009 World Scientific Publishing Company. 2009 Journal Article http://hdl.handle.net/20.500.11937/42759 10.1142/S0218001409006977 restricted |
| spellingShingle | Yeong, L. Ang, L. Lim, Hann Seng, K. Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| title | Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| title_full | Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| title_fullStr | Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| title_full_unstemmed | Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| title_short | Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| title_sort | face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic supervised forward propagation network |
| url | http://hdl.handle.net/20.500.11937/42759 |