Restoration of Partially Occluded Shapes of Faces using Neural Networks

Book chapter


Draganova, Chrisina, Lanitis, Andreas and Christodoulou, Chris 2005. Restoration of Partially Occluded Shapes of Faces using Neural Networks. in:
AuthorsDraganova, Chrisina, Lanitis, Andreas and Christodoulou, Chris
Abstract

One of the major difficulties encountered in the development of face image processing algorithms, is the possible presence of occlusions that hide part of the face images to be processed. Typical examples of facial occlusions include sunglasses, beards, hats and scarves. In our work we address the problem of restoring the overall shape of faces given only the shape presentation of a small part of the face. In the experiments described in this paper the shape of a face is defined by a series of landmarks located on the face outline and on the outline of different facial features. We describe the use of a number of methods including a method that utilizes a Hopfield neural network, a method that uses Multi-Layer Perceptron (MLP) neural network, a novel technique which combines Hopfield and MLP together, and a method based on associative search. We analyze comparative experiments in order to assess the performance of the four methods mentioned above. According to the experimental results it is possible to recover with reasonable accuracy the overall shape of faces even in the case that a substantial part of the shape of a given face is not visible. The techniques presented could form the basis for developing face image processing systems capable of dealing with occluded faces.

Keywordsfacial imaging; facial recognition systems; Multi-Layer Perceptron (MLP) neural network
Year2005
Publication dates
Print2005
Publication process dates
Deposited23 Feb 2010
ISSN1615-3871
1860-0794
Web address (URL)http://dx.doi.org/10.1007/3-540-32390-2_90
http://hdl.handle.net/10552/617
Additional information

Citation:
Draganova, C., Lanitis, A., Christodulou, C., (2005) ‘Restoration of Partially Occluded Shapes of Faces using Neural Networks’ In: Computer Recognition Systems, Berlin: Springer-Verlag, vol. 30 pp 767-775..

Accepted author manuscript
License
CC BY-ND
Permalink -

https://repository.uel.ac.uk/item/86837

Download files

Accepted author manuscript
  • 24
    total views
  • 95
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as