Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System
Automatic face detection is mainly the first step for most of the face-based biometric systems today such as face recognition, facial expression recognition, and tracking head pose. However, face detection technology has various drawbacks caused by challenges in indoor and outdoor environment suc...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/45941/ http://eprints.usm.my/45941/1/Development%20Of%20Hierarchical%20Skin-Adaboost-Neural%20Network%20%28H-Skann%29%20For%20Multiface%20%20Detection%20In%20Video%20Surveillance%20System.pdf |
| _version_ | 1848880468259241984 |
|---|---|
| author | Zakaria, Zulhadi |
| author_facet | Zakaria, Zulhadi |
| author_sort | Zakaria, Zulhadi |
| building | USM Institutional Repository |
| collection | Online Access |
| description | Automatic face detection is mainly the first step for most of the face-based
biometric systems today such as face recognition, facial expression recognition, and
tracking head pose. However, face detection technology has various drawbacks caused
by challenges in indoor and outdoor environment such as uncontrolled lighting and
illumination, features occlusions and pose variation. This thesis proposed a technique
to detect multiface in video surveillance application with strategic architecture
algorithm based on the hierarchical and structural design. This technique consists of
two major blocks which are known as Face Skin Localization (FSL) and Hierarchical
Skin Area (HSA). FSL is formulated to extract valuable skin data to be processed at
the first stage of system detection, which also includes Face Skin Merging (FSM) in
order to correctly merge separated skin areas. HSA is proposed to extend the searching
of face candidates in selected segmentation area based on the hierarchical architecture
strategy, in which each level of the hierarchy employs an integration of Adaboost and
Neural Network Algorithm. Experiments were conducted on eleven types database
which consists of various challenges to human face detection system. Results reveal
that the proposed H-SKANN achieves 98.03% and 97.02% of of averaged accuracy
for benchmark database and surveillance area databases, respectively. |
| first_indexed | 2025-11-15T18:03:36Z |
| format | Thesis |
| id | usm-45941 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T18:03:36Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-459412021-11-17T03:42:16Z http://eprints.usm.my/45941/ Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System Zakaria, Zulhadi T Technology Automatic face detection is mainly the first step for most of the face-based biometric systems today such as face recognition, facial expression recognition, and tracking head pose. However, face detection technology has various drawbacks caused by challenges in indoor and outdoor environment such as uncontrolled lighting and illumination, features occlusions and pose variation. This thesis proposed a technique to detect multiface in video surveillance application with strategic architecture algorithm based on the hierarchical and structural design. This technique consists of two major blocks which are known as Face Skin Localization (FSL) and Hierarchical Skin Area (HSA). FSL is formulated to extract valuable skin data to be processed at the first stage of system detection, which also includes Face Skin Merging (FSM) in order to correctly merge separated skin areas. HSA is proposed to extend the searching of face candidates in selected segmentation area based on the hierarchical architecture strategy, in which each level of the hierarchy employs an integration of Adaboost and Neural Network Algorithm. Experiments were conducted on eleven types database which consists of various challenges to human face detection system. Results reveal that the proposed H-SKANN achieves 98.03% and 97.02% of of averaged accuracy for benchmark database and surveillance area databases, respectively. 2017-04-01 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/45941/1/Development%20Of%20Hierarchical%20Skin-Adaboost-Neural%20Network%20%28H-Skann%29%20For%20Multiface%20%20Detection%20In%20Video%20Surveillance%20System.pdf Zakaria, Zulhadi (2017) Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System. PhD thesis, Universiti Sains Malaysia. |
| spellingShingle | T Technology Zakaria, Zulhadi Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System |
| title | Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System |
| title_full | Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System |
| title_fullStr | Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System |
| title_full_unstemmed | Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System |
| title_short | Development Of Hierarchical Skin-Adaboost-Neural Network (H-Skann) For Multiface Detection In Video Surveillance System |
| title_sort | development of hierarchical skin-adaboost-neural network (h-skann) for multiface detection in video surveillance system |
| topic | T Technology |
| url | http://eprints.usm.my/45941/ http://eprints.usm.my/45941/1/Development%20Of%20Hierarchical%20Skin-Adaboost-Neural%20Network%20%28H-Skann%29%20For%20Multiface%20%20Detection%20In%20Video%20Surveillance%20System.pdf |