Please wait a minute...
ZJUS-A
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering)  2009, Vol. 10 Issue (2): 232-238    DOI: 10.1631/jzus.A0820138
Electrical & Electronic Engineering     
Patch-guided facial image inpainting by shape propagation
Yue-ting ZHUANG, Yu-shun WANG, Timothy K. SHIH, Nick C. TANG
Institute of Artificial Intelligence, School of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; Department of Computer Science, National Taipei University of Education, Taipei 10671, Taiwan, China; Department of Computer Science and Information Engineering, Tamkang University, Taipei 25137, Taiwan, China
Download:     PDF (0 KB)     
Export: BibTeX | EndNote (RIS)      

Abstract  Images with human faces comprise an essential part in the imaging realm. Occlusion or damage in facial portions will bring a remarkable discomfort and information loss. We propose an algorithm that can repair occluded or damaged facial images automatically, named ‘facial image inpainting’. Inpainting is a set of image processing methods to recover missing image portions. We extend the image inpainting methods by introducing facial domain knowledge. With the support of a face database, our approach propagates structural information, i.e., feature points and edge maps, from similar faces to the missing facial regions. Using the inferred structural information as guidance, an exemplar-based image inpainting algorithm is employed to copy patches in the same face from the source portion to the missing portion. This newly proposed concept of facial image inpainting outperforms the traditional inpainting methods by propagating the facial shapes from a face database, and avoids the problem of variations in imaging conditions from different images by inferring colors and textures from the same face image. Our system produces seamless faces that are hardly seen drawbacks.

Key words： Image inpainting      Face reconstruction      Feature point extraction     
Received: 26 February 2008     
CLC:  TP391.41  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Yue-ting ZHUANG
Yu-shun WANG
Timothy K. SHIH
Nick C. TANG
Cite this article:

Yue-ting ZHUANG, Yu-shun WANG, Timothy K. SHIH, Nick C. TANG. Patch-guided facial image inpainting by shape propagation. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(2): 232-238.

URL:

http://www.zjujournals.com/xueshu/zjus-a/10.1631/jzus.A0820138     OR     http://www.zjujournals.com/xueshu/zjus-a/Y2009/V10/I2/232

[1] ZHANG Jian, ZHUANG Yue-ting. Sample based 3D face reconstruction from a single frontal image by adaptive locally linear embedding[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2007, 8(4): 550-558.
[2] Wang Qian-Ting, Guo Jian, Chen Yi-Zhi. Fractal modelling of off-road terrain oriented to vehicle virtual test[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(Supplement 2): 287-292.
[3] LI Zhong, MA Li-zhuang, TAN Wu-zheng, ZHAO Ming-xi. Reconstruction from contour lines based on bi-cubic Bézier spline surface[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(7 ): 18-.
[4] WANG Qiang, ZHENG Yao, CHEN Chun, TADAHIRO Fujimoto, CHIBA Norishige. Efficient rendering of breaking waves using MPS method[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(6 ): 13-.
[5] DONG Chen-shi, WANG Guo-zhao. Surface reconstruction by offset surface filtering[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2005, 6(Supplement 1): 137-143.
[6] SHIH Timothy K., CHANG Rong-chi. Super-resolution inpainting[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2005, 6( 6): 2-.