Chinese Calligraphy Character Image Synthesis Based on Retrieval

Authors:
Xiafen Zhang;Guangzhong Liu
Affiliations:
College of Information Engineering, Shanghai Maritime University, Shanghai, P.R. China;College of Information Engineering, Shanghai Maritime University, Shanghai, P.R. China
Venue:
PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2009

Citing 9
Cited 0

Multiresolution mesh morphing

Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Deformable Contours: Modeling and Extraction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Generation of Artistic Chinese Calligraphy

IEEE Intelligent Systems
Handwriting Matching and Its Application to Handwriting Synthesis

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Robust Point Matching for Nonrigid Shapes by Preserving Local Neighborhood Structures

IEEE Transactions on Pattern Analysis and Machine Intelligence
Capturing Character Contours from Images of Ancient Chinese Calligraphy

DMAMH '07 Proceedings of the Second Workshop on Digital Media and its Application in Museum & Heritage
A Quick Search Engine for Historical Chinese Calligraphy Character Image

CISP '08 Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 1 - Volume 01
Skeleton-Based Recognition of Chinese Calligraphic Character Image

PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Retrieval of chinese calligraphic character image

PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Chinese calligraphy works is a valuable culture heritage written by soft brush. They were scanned into image format, stored in computer in order to enable universal and convenient access. However, the retrieved calligraphy candidates may not satisfy user's expectation due to the size limitation of calligraphy database. This paper propose a way to offer new calligraphy candidates by synthesizing based on the retrieved calligraphy: First, characters contours are extracted to represent calligraphy style. Second, shape matrixes are constructed and peer-to-peer contour points are figured out. Then new calligraphy character candidates that in some degree looks like the retrieved calligraphy characters are generated by employing g-snake algorithm. Finally, the effect of the approach is demonstrated by the implementation.