dc.contributor.author | Jayne, C. | en |
dc.contributor.author | Lanitis, A. | en |
dc.contributor.author | Christodoulou, Chris C. | en |
dc.creator | Jayne, C. | en |
dc.creator | Lanitis, A. | en |
dc.creator | Christodoulou, Chris C. | en |
dc.date.accessioned | 2019-11-13T10:40:25Z | |
dc.date.available | 2019-11-13T10:40:25Z | |
dc.date.issued | 2012 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/54111 | |
dc.description.abstract | This paper investigates the performance of neural network-based techniques applied to the problem of defining the relationship between a particular type of variation in face images and the multivariate data distributions of these images. In this respect the problem of defining a mapping associating a quantified facial attribute and the overall typical facial appearance is addressed. In particular the applicability of formulating a mapping function using neural network-based methods like Multilayer Perceptrons (MLPs), Radial Basis Functions (RBFs), Mixture Density Networks (MDNs) and a latent variable method, the General Topographic Mapping (GTM) is investigated. Quantitative and visual results obtained during the experimental investigation, suggest that for one-to-many problems, where the entire variance of the distribution is not required, the RBFs are the best options when compared to MLPs, MDNs and GTM. The proposed techniques can be applied to applications involving face image synthesis and other applications that require one-to-many mapping transformations. © 2012 Elsevier Ltd. All rights reserved. | en |
dc.source | Expert Systems with Applications | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84859213756&doi=10.1016%2fj.eswa.2012.02.177&partnerID=40&md5=3f5aecb84c5ac2e85bb71e04806b525e | |
dc.subject | Radial basis functions | en |
dc.subject | Neural networks | en |
dc.subject | Conformal mapping | en |
dc.subject | Experimental investigations | en |
dc.subject | Image segmentation | en |
dc.subject | Radial basis function networks | en |
dc.subject | Latent variable methods | en |
dc.subject | Mapping functions | en |
dc.subject | Mixture density | en |
dc.subject | Multivariate data | en |
dc.subject | Network-based | en |
dc.subject | Topographic mapping | en |
dc.subject | Face image synthesis | en |
dc.subject | Face images | en |
dc.subject | Facial appearance | en |
dc.subject | Isolating sources | en |
dc.subject | Isolating sources of variation | en |
dc.subject | Network mapping | en |
dc.subject | One-to-many mapping | en |
dc.subject | Other applications | en |
dc.title | One-to-many neural network mapping techniques for face image synthesis | en |
dc.type | info:eu-repo/semantics/article | |
dc.identifier.doi | 10.1016/j.eswa.2012.02.177 | |
dc.description.volume | 39 | |
dc.description.issue | 10 | |
dc.description.startingpage | 9778 | |
dc.description.endingpage | 9787 | |
dc.author.faculty | 002 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences | |
dc.author.department | Τμήμα Πληροφορικής / Department of Computer Science | |
dc.type.uhtype | Article | en |
dc.description.notes | <p>Cited By :2</p> | en |
dc.source.abbreviation | Expert Sys Appl | en |
dc.contributor.orcid | Christodoulou, Chris C. [0000-0001-9398-5256] | |
dc.gnosis.orcid | 0000-0001-9398-5256 | |