Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/7201
Title: Improving the robustness of subspace learning techniques for facial expression recognition
Authors: Bolis, Dimitris
Tefas, Anastasios
Pitas, Ioannis K.
Maronidis, Anastasios
Keywords: Facial expression
Neural networks
Experiments
Human face recognition (Computer science)
Issue Date: 2010
Publisher: Springer Berlin Heidelberg
Source: 20th International Conference on Artificial Neural Networks, 2010, Thessaloniki, Greece
Abstract: In this paper, the robustness of appearance-based, subspace learning techniques for facial expression recognition in geometrical transformations is explored. A plethora of facial expression recognition algorithms is presented and tested using three well-known facial expression databases. Although, it is common-knowledge that appearance based methods are sensitive to image registration errors, there is no systematic experiment reported in the literature and the problem is considered, a priori, solved. However, when it comes to automatic real-world applications, inaccuracies are expected, and a systematic preprocessing is needed. After a series of experiments we observed a strong correlation between the performance and the bounding box position. The mere investigation of the bounding box’s optimal characteristics is insufficient, due to the inherent constraints a real-world application imposes, and an alternative approach is demanded. Based on systematic experiments, the database enrichment with translated, scaled and rotated images is proposed for confronting the low robustness of subspace techniques for facial expression recognition.
URI: http://ktisis.cut.ac.cy/handle/10488/7201
DOI: 10.1007/978-3-642-15819-3_63
Rights: © 2010 Springer-Verlag Berlin Heidelberg.
Appears in Collections:Δημοσιεύσεις σε συνέδρια/Conference papers

Show full item record

SCOPUSTM   
Citations 50

1
checked on May 20, 2017

Page view(s)

7
Last Week
0
Last month
2
checked on Jul 21, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.