摘要
This paper describes a new framework for reusing hand-drawn cartoon clips based on language understanding ap- proach. Our framework involves two stages: a preprocessing phase, in which a hand-drawn clip library with mixed architecture is constructed, and the on-line phase, in which the domain dependent language instructions parsing is carried out and clips in the clip library are matched by use of some matching values calculated from the information derived from instruction parsing. An im- portant feature of our approach is its ability to preserve the artistic quality of clips in the produced cartoon animations.
This paper describes a new framework for reusing hand-drawn cartoon clips based on language understanding approach. Our framework involves two stages： a preprocessing phase, in which a hand-drawn clip library with mixed architecture is constructed, and the on-line phase, in which the domain dependent language instructions parsing is carried out and clips in the clip library are matched by use of some matching values calculated from the information derived from instruction parsing. An important feature of our approach is its ability to preserve the artistic quality of clips in the produced cartoon animations.
基金
Project supported by the National Natural Science Foundation of China (No. 60373037), the Hi-Tech Research and Development Pro-gram (863) of China (No. 2004AA119060), Natural Science Founda-tion of Zhejiang Province (No. M603228), Zhejiang Science and Technology Plan Project, and Ningbo Science Foundation for Doctor, China
