Identification of facial features on Android platforms
- Authors: Mawafo, Josette C. Tagatio , Clarke, W. A. , Robinson, P. E.
- Date: 2013
- Subjects: Identification - Facial features , Android , Android platforms - Facial feature identification
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16357 , uj:15766 , Mawafo, J.C.T., Clarke, W.A. & Robinson, P.E. 2013. Identification of facial features on Android platforms. IEEE International Conference on Industrial Technology (ICIT 2013)
- Description: Abstract: In this paper, we present and investigate the performance of an algorithm designed to identify facial features on an android mobile platform. Facial feature identification is the necessary step before many computer vision systems including emotion detection, face tracking and face recognition. The facial feature identification algorithm presented is based on an anthropometric face model , box-blur filtering, and nonmaximum suppression to find eyes corners, mouth corners and nose centre. Skin colour detection is used to find regions in the image that have a higher potential of containing eyes. The anthropometric face model is used to reduce the computational complexity involved in localising facial regions. This algorithm is designed to be compatible with the limited hardware and memory capabilities of mobile devices.
- Full Text:
Mitigation of atmospheric turbulence distortions in long range video surveillance
- Authors: Robinson, P. E. , Clarke, W. A.
- Date: 2011
- Subjects: Atmospheric turbulence , Scintillation , Heat shimmer , Graphics processing units , Optical flow , Deblurring , Quality metrics
- Type: Article
- Identifier: http://hdl.handle.net/10210/16412 , uj:15771 , Citation: Robinson, P.E. & Clarke, W.A. 2011. Mitigation of atmospheric turbulence distortions in long range video surveillance, SAIEE Africa Research Journal, 102(1) March:16-28.
- Description: Abstract: This paper explores the problem of atmospheric turbulence in long range video surveillance. This turbulence causes a phenomenon called heat scintillation or heat shimmer which introduces distortions into the video being captured. The nature of these distortions is discussed and a number of possible solutions explored.
- Full Text:
Modelling distances between genetically related languages using an extended weighted Levenshtein distance
- Authors: Paluncic, F. , Ferreira, Hendrik C. , Swart, Theo G. , Clarke, W. A.
- Date: 2009
- Subjects: Levenshtein distance , Insertion/deletion
- Language: English
- Type: Abstract
- Identifier: http://hdl.handle.net/10210/21309 , uj:16139 , ISSN: 1607-3614 , DOI: 10.2989/SALALS.2009.27.4.2.1022 , Citation: Paluncic, F. et al. 2009. Modelling distances between genetically related languages using an extended weighted Levenshtein distance. Southern African Linguistics and Applied Language Studies Journal, 27(4):381-389. DOI: 10.2989/SALALS.2009.27.4.2.1022.
- Description: Abstract: This article proposes the use of an extended weighted Levenshtein distance to model the time depth between parent and direct descendant languages and also the dialectal separation between sibling languages. The parent language is usually a proto-language, a hypothetical reconstructed language, whose precise date is usually conjectural. Phonology is used as an indicator of language difference, which is modelled by means of an extended weighted Levenshtein distance. This idea is applied specifically to the Iranian language family.
- Full Text:
Comparison of principal component analysis and linear discriminant analysis for face recognition (March 2007)
- Authors: Robinson, P. E. , Clarke, W. A.
- Date: 2007
- Subjects: Face recognition , Eigenfaces , Fisherfaces , Principal component analysis , Linear discriminant analysis
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16300 , uj:15759 , Robinson, P.E. & Clarke, W.A. Comparison of Principal Component Analysis and Linear Discriminant Analysis for face recognition (March 2007), in AFRICON 2007:1-6
- Description: Abstract: In this paper two Face Recognition techniques, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), are considered and implemented using a Nearest Neighbor classifier. The performance of the two techniques is then compared in facial recognition and detection tasks. The comparisons are done using a facial recognition database captured for the project that contains images captured over a range of poses, lighting conditions and occlusions.
- Full Text: