The nature of statistical learning theory
The nature of statistical learning theory
IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstruction of Partially Damaged Face Images Based on a Morphable Face Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Person identification from heavily occluded face images
Proceedings of the 2004 ACM symposium on Applied computing
Automatic Eyeglasses Removal from Face Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Generalized EM Approach for 3D Model Based Face Recognition under Occlusions
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Reconstruction of Partially Occluded Face by Fast Recursive PCA
CISW '07 Proceedings of the 2007 International Conference on Computational Intelligence and Security Workshops
Glasses removal from facial image using recursive PCA reconstruction
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Gabor feature based sparse representation for face recognition with gabor occlusion dictionary
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Three-Dimensional Occlusion Detection and Restoration of Partially Occluded Faces
Journal of Mathematical Imaging and Vision
Recognizing occluded faces by exploiting psychophysically inspired similarity maps
Pattern Recognition Letters
Hi-index | 0.00 |
Byzantine art is overwhelmed by a multitude of icons that portray sacred faces. However, a large number of icons of historical value are either partially or totally damaged and thus in need of undergoing conservation. The detection and assessment of damage in cultural heritage artifacts comprise an integral part of the conservation process. In this paper, a method that can be used for assessing the damage on faces appearing in Byzantine icons is presented. The main approach involves the estimation of the residuals obtained after the coding and reconstruction of face image regions using trained Principal Component Analysis texture models. The extracted residuals can be used as the basis for obtaining information about the amount of damage and the positions of the damaged regions. Due to the specific nature of Byzantine icons several variations of the basic approach are tested through a quantitative experimental evaluation so that the methods most suited to the specific application domain are identified. As part of the experimental evaluation, holistic as well as patch-decomposition techniques have been utilized in order to catch the global and local information of the images, respectively. According to the results it is possible to detect and localize with reasonable accuracy the damaged areas of faces appearing in Byzantine icons.