ML Anthology

Efficient Search of Faces from Complex Line Drawings

Jianzhuang Liu, Xiaoou Tang
CVPR 2004 pp. 791-796
doi:10.1109/CVPR.2004.91 /cvpr/2004/liu2004cvpr-efficient/

Abstract

Single 2D line drawing is a straightforward method to illustrate 3D objects. The faces of an object depicted by a line drawing give very useful information for the reconstruction of its 3D geometry. Each of the two recently proposed methods for face identification from line drawings involves two combinatorial problems. When dealing with complex objects having more faces, the combinatorial explosion prevents these methods from practical uses. This paper proposes a new approach to tackling the face identification problem by a variable-length genetic algorithm (GA) with geometric constraints and a novel heuristic incorporated for local search. The hybrid GA solves the two combinatorial problems simultaneously. Experimental results show that our algorithm can find the faces of a line drawing having more than 30 faces much more efficiently.

PDF CVPR Semantic Scholar

Cite

Text

Liu and Tang. "Efficient Search of Faces from Complex Line Drawings." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.91

Markdown

[Liu and Tang. "Efficient Search of Faces from Complex Line Drawings." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/liu2004cvpr-efficient/) doi:10.1109/CVPR.2004.91

BibTeX

@inproceedings{liu2004cvpr-efficient,
  title     = {{Efficient Search of Faces from Complex Line Drawings}},
  author    = {Liu, Jianzhuang and Tang, Xiaoou},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {791-796},
  doi       = {10.1109/CVPR.2004.91},
  url       = {https://mlanthology.org/cvpr/2004/liu2004cvpr-efficient/}
}