http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Character Modeling and Synthesis from Human Handwriting Motions with Esthetic Evaluation
Hiroyuki Fujioka,Hiroyuki Kano 한국과학기술원 인간친화 복지 로봇 시스템 연구센터 2007 International Journal of Assistive Robotics and Me Vol.8 No.4
We develop a scheme for constructing character font models from human handwriting data. First, handwriting motions are measured using a pen-tablet device, and stored as a 3-dimensional time series data. Then, the data is used to construct characters by employing B-splines and the theory of smoothing splines based on the minimum hand jerk model. We can then synthesize arbitrary words with arbitrary cursiveness. Moreover, by employing the concept of Induction Field in Vision, we propose a tuning method of the so-called smoothing parameter from an esthetic viewpoint of the resulting cursive characters. The effectiveness of the developed method is verified by some experiments, including those on calligraphic learning.
Design of Cursive Handwriting Characters Using Esthetic Evaluation
Shinya Miyata,Hiroyuki Fujioka 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
This paper considers the problem for constructing characters from handwriting experiments. First, handwriting motions are measured using a pen-tablet and stored as a 3-dimensional time series data. Then, the data is used to construct characters by employing the ‘dynamic font’ model and the theory of smoothing splines based on the minimum jerk model. Also, we propose a method for designing cursive characters from an esthetic viewpoint. In addition, the problem for positioning optimally characters is considered. The effectiveness of the method is verified by experimental study.
Rachanart Soontornvorn,Hiroyuki Fujioka 대한전자공학회 2019 IEIE Transactions on Smart Processing & Computing Vol.8 No.2
In this paper, we consider the problem of representing some given planar curves on a two-dimensional plane as so-called compact B-spline curves by using only the dominant control points. In particular, we here develop a method for selecting the dominant control points by introducing the dynamic programming (DP) approach and a new idea of knot points selection using a multi-level error function where the term multi-level means that not only function values of a given curve are considered, but also the derivatives. Moreover, we offer a way to represent compact planar B-spline curves using non-uniform rational B-splines (NURBS). We demonstrate performance with experimental studies using handwriting data. The results of this paper will be useful for improving usability in the design of the so-called dynamic font-based characters.