Izvorni znanstveni članak

https://doi.org/10.17559/TV-20150612175259

Image abstraction painting of flow-like stylization

Qian Wenhua ; Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650091, China
Xu Dan ; Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650091, China
Yue Kun ; Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650091, China
Guan Zheng ; Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650091, China

Sažetak

This paper presents a non-photorealistic rendering technique for producing flow-like abstraction stylization from a photograph. Based on anisotropic Kuwahara filtering in conjunction with line integral convolution, our method abstracts shapes and colors simultaneously while preserving features of images. In particular, we develop an edge detection and dilation method, to draw attention to salient features and image boundaries. This proposed algorithm is incremental and iterative, and therefore the degree of flow and abstraction can be controlled. Experimental results demonstrate that the effectiveness of our method in producing a coherent and flow-like abstraction stylization is satisfactory yet preserving features and directions from photographs.

Ključne riječi

non-photorealistic rendering; abstraction; flow like; anisotropic filter; LIC (Line Integral Convolution)

Hrčak ID:

143085

URI

https://hrcak.srce.hr/143085

Datum izdavanja:

8.8.2015.

Podaci na drugim jezicima: hrvatski

Posjeta: 2.422 *