Integrated face and facial components detection
This paper presents an algorithm that detects faces and facial features (eyes, nose and mouth) on images captured by CCTV system under various imaging conditions, such as variation in poses, scale, illumination and occlusion. The system detects face, nose and mouth using three different classifiers,...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
2015
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/14337/1/Integrated%20face%20and%20facial%20components%20detection.pdf |
| _version_ | 1825945408332890112 |
|---|---|
| author | Ho, Lip Chin Hanafi, Marsyita Salka, Tanko Danial |
| author_facet | Ho, Lip Chin Hanafi, Marsyita Salka, Tanko Danial |
| author_sort | Ho, Lip Chin |
| collection | UPM |
| description | This paper presents an algorithm that detects faces and facial features (eyes, nose and mouth) on images captured by CCTV system under various imaging conditions, such as variation in poses, scale, illumination and occlusion. The system detects face, nose and mouth using three different classifiers, which were created based on the Viola-Jones method [1] and the eyes were detected using an Eye Detection method that consists of resolution reduction, identification of the eye candidates using eye filter [2] and eyes localization based on mean comparison. Experimented on 500 images, the algorithm produced 98.4% accuracy for face, 98.8% for nose, 95.6% for mouth and 94.8% for eyes. |
| first_indexed | 2024-03-06T07:31:04Z |
| format | Conference or Workshop Item |
| id | upm.eprints-14337 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T07:31:04Z |
| publishDate | 2015 |
| publisher | IEEE |
| record_format | dspace |
| spelling | upm.eprints-143372019-04-08T08:31:45Z http://psasir.upm.edu.my/id/eprint/14337/ Integrated face and facial components detection Ho, Lip Chin Hanafi, Marsyita Salka, Tanko Danial This paper presents an algorithm that detects faces and facial features (eyes, nose and mouth) on images captured by CCTV system under various imaging conditions, such as variation in poses, scale, illumination and occlusion. The system detects face, nose and mouth using three different classifiers, which were created based on the Viola-Jones method [1] and the eyes were detected using an Eye Detection method that consists of resolution reduction, identification of the eye candidates using eye filter [2] and eyes localization based on mean comparison. Experimented on 500 images, the algorithm produced 98.4% accuracy for face, 98.8% for nose, 95.6% for mouth and 94.8% for eyes. IEEE 2015 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/14337/1/Integrated%20face%20and%20facial%20components%20detection.pdf Ho, Lip Chin and Hanafi, Marsyita and Salka, Tanko Danial (2015) Integrated face and facial components detection. In: 2015 Seventh International Conference on Computational Intelligence, Modelling and Simulation (CIMSim 2015), 27-29 July 2015, Kuantan, Pahang, Malaysia. (pp. 87-91). 10.1109/CIMSim.2015.16 |
| spellingShingle | Ho, Lip Chin Hanafi, Marsyita Salka, Tanko Danial Integrated face and facial components detection |
| title | Integrated face and facial components detection |
| title_full | Integrated face and facial components detection |
| title_fullStr | Integrated face and facial components detection |
| title_full_unstemmed | Integrated face and facial components detection |
| title_short | Integrated face and facial components detection |
| title_sort | integrated face and facial components detection |
| url | http://psasir.upm.edu.my/id/eprint/14337/1/Integrated%20face%20and%20facial%20components%20detection.pdf |
| work_keys_str_mv | AT holipchin integratedfaceandfacialcomponentsdetection AT hanafimarsyita integratedfaceandfacialcomponentsdetection AT salkatankodanial integratedfaceandfacialcomponentsdetection |