Analysis of cypriot icon faces using ICA-enhanced active shape model representation

Authors:
Guifang Duan;Neela Sawant;James Z. Wang;Dean Snow;Danni Ai;Yen-Wei Chen
Affiliations:
Ritsumeikan University, Kusatsu, Japan;The Pennsylvania State University, University Park, USA;The Pennsylvania State University/National Science Foundation, Arlington, USA;The Pennsylvania State University, University Park, USA;Ritsumeikan University, Kusatsu, Japan;Ritsumeikan University, Kusatsu, Japan
Venue:
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Year:
2011

Citing 8
Cited 0

Active shape models—their training and application

Computer Vision and Image Understanding
Independent component analysis: algorithms and applications

Neural Networks
Robust Real-Time Face Detection

International Journal of Computer Vision
Image Indexing and Retrieval for a Vietnamese Folk Paintings Gallery

DICTA '05 Proceedings of the Digital Image Computing on Techniques and Applications
An effective method to detect and categorize digitized traditional Chinese paintings

Pattern Recognition Letters
Semantic Classification of Byzantine Icons

IEEE Intelligent Systems
Independent component analysis based ring artifact reduction in cone-beam CT images

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Studying digital imagery of ancient paintings by mixtures of stochastic models

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Religious iconography is an integral component of the cultural heritage of Cyprus, which was once a part of the great Byzantine empire. On one hand, icons exhibit strict adherence to conventional symbols, poses and apparel. On the other hand, there is a great variety in the style of depiction that can be attributed to different schools and periods. This paper proposes an active shape model (ASM) based technique for icon face representation that can be used for style comparison and attribution. For centuries-old icons suffering from loss of paint, cracks and added noise from digitization artifacts, we apply an independent component analysis (ICA) technique to enhance the paintings' original work. The experimental results show that our method can effectively characterize Cypriot icons.