Title :
A novel math method of image morphing
Author :
Shoujue Wang ; Xianyang Liang
Author_Institution :
Lab. of Artificial Neural Networks, Chinese Acad. of Sci., Beijing, China
Abstract :
Image morphing has received much attention in recent years. It mainly involves feature specification, geometric transformation and color blending. Here, a novel calculation method of image morphing is proposed. First, a novel coordinate system called triangle coordinate system is defined, which has a great advantage in geometric transformation. Second, corresponding feature points on images are marked. Third, cartesian coordinates of all pixels are converted into triangle coordinates for geometric transformation. Finally, color is blended and interpolated. Experiments given in the paper show that the method proposed is practicable.
Keywords :
geometry; image colour analysis; image morphing; image resolution; color blending; feature specification; geometric transformation; image morphing; pixels; triangle coordinates; Face; Feature extraction; Image color analysis; Interpolation; Pixel; Transforms; Geometric transformation; Image morphing; Topological deformation; Triangle coordinate system;
Conference_Titel :
Computer Research and Development (ICCRD), 2011 3rd International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-61284-839-6
DOI :
10.1109/ICCRD.2011.5763867