Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2012, Vol. 13 Issue (3): 196-207    DOI: 10.1631/jzus.C1100202
    
Synthesizing style-preserving cartoons via non-negative style factorization
Zhang Liang, Jun Xiao, Yue-ting Zhuang
Institute of Artificial Intelligence, School of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  We present a complete framework for synthesizing style-preserving 2D cartoons by learning from traditional Chinese cartoons. In contrast to reusing-based approaches which rely on rearranging or retrieving existing cartoon sequences, we aim to generate stylized cartoons with the idea of style factorization. Specifically, starting with 2D skeleton features of cartoon characters extracted by an improved rotoscoping system, we present a non-negative style factorization (NNSF) algorithm to obtain style basis and weights and simultaneously preserve class separability. Thus, factorized style basis can be combined with heterogeneous weights to re-synthesize style-preserving features, and then these features are used as the driving source in the character reshaping process via our proposed subkey-driving strategy. Extensive experiments and examples demonstrate the effectiveness of the proposed framework.

Key wordsCharacter cartoon      Machine learning      Cartoon synthesis     
Received: 08 July 2011      Published: 01 March 2012
CLC:  TP391  
Cite this article:

Zhang Liang, Jun Xiao, Yue-ting Zhuang. Synthesizing style-preserving cartoons via non-negative style factorization. Front. Inform. Technol. Electron. Eng., 2012, 13(3): 196-207.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1100202     OR     http://www.zjujournals.com/xueshu/fitee/Y2012/V13/I3/196


Synthesizing style-preserving cartoons via non-negative style factorization

We present a complete framework for synthesizing style-preserving 2D cartoons by learning from traditional Chinese cartoons. In contrast to reusing-based approaches which rely on rearranging or retrieving existing cartoon sequences, we aim to generate stylized cartoons with the idea of style factorization. Specifically, starting with 2D skeleton features of cartoon characters extracted by an improved rotoscoping system, we present a non-negative style factorization (NNSF) algorithm to obtain style basis and weights and simultaneously preserve class separability. Thus, factorized style basis can be combined with heterogeneous weights to re-synthesize style-preserving features, and then these features are used as the driving source in the character reshaping process via our proposed subkey-driving strategy. Extensive experiments and examples demonstrate the effectiveness of the proposed framework.

关键词: Character cartoon,  Machine learning,  Cartoon synthesis 
[1] Mohammad Mosleh, Hadi Latifpour, Mohammad Kheyrandish, Mahdi Mosleh, Najmeh Hosseinpour. A robust intelligent audio watermarking scheme using support vector machine[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(12): 1320-1330.
[2] G. R. Brindha, P. Swaminathan, B. Santhi. Performance analysis of new word weighting procedures for opinion mining[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(11): 1186-1198.
[3] Fei-wei Qin, Lu-ye Li, Shu-ming Gao, Xiao-ling Yang, Xiang Chen. A deep learning approach to the classification of 3D CAD models[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(2): 91-106.
[4] Yun-hua Qu, Tian-jiong Tao, Serge Sharoff, Narisong Jin, Ruo-yuan Gao, Nan Zhang, Yu-ting Yang, Cheng-zhi Xu. Using an integrated feature set to generalize and justify the Chinese-to-English transferring rule of the ‘ZHE’ aspect[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(9): 663-676.