Detecting Chinese calligraphy style consistency by deep learning and one-class SVM

doi:10.1109/ICIVC.2017.7984523

	Detecting Chinese calligraphy style consistency by deep learning and one-class SVM
	Jiulong Z.3; Luming G.3; Su Y.3; Sun X.1; Li X.4
	2017-07-18
Source Publication	2017 2nd International Conference on Image, Vision and Computing, ICIVC 2017
Pages	83-86
Abstract	When beginners practice Chinese calligraphy, they often copy from ancient calligraphic works and try to imitate the style as closely as possible. However there are inevitably some characters whose styles are not correctly followed. Thus we are motivated to detect the style consistency of all written characters in one practice. With the styles extracted by using stacked autoencoders of deep neural network model, we discriminate correctly styled and alien styled characters using a trained one-class support vector machine. Thus we can pick out those outliers. The proposed algorithm reaches satisfactory results. The algorithm can also be applied to other image style detection problems.
Keyword	Calligraphy style Chinese calligraphy Deep learning Feature extraction
DOI	10.1109/ICIVC.2017.7984523
URL	View the original
Language	英語
全文获取链接	View Full-Text via DOI View Full-Text via Scopus
引用统计
Document Type	Conference paper
专题	University of Macau
Affiliation	1.University of Chinese Academy of Sciences 2.Fudan University 3.Xi'an University of Technology 4.Universidade de Macau
推荐引用方式 GB/T 7714	Jiulong Z.,Luming G.,Su Y.,et al. Detecting Chinese calligraphy style consistency by deep learning and one-class SVM[C],2017:83-86.