Sciweavers

309 search results - page 34 / 62
» Word Image Matching Based on Hausdorff Distances
Sort
View
CIVR
2005
Springer
14 years 1 months ago
EMD-Based Video Clip Retrieval by Many-to-Many Matching
This paper presents a new approach for video clip retrieval based on Earth Mover’s Distance (EMD). Instead of imposing one-to-one matching constraint as in [11, 14], our approach...
Yuxin Peng, Chong-Wah Ngo
BMVC
2010
13 years 5 months ago
Evaluation of dimensionality reduction methods for image auto-annotation
Image auto-annotation is a challenging task in computer vision. The goal of this task is to predict multiple words for generic images automatically. Recent state-of-theart methods...
Hideki Nakayama, Tatsuya Harada, Yasuo Kuniyoshi
PAMI
2007
152views more  PAMI 2007»
13 years 7 months ago
DCT-Based Iris Recognition
—This paper presents a novel iris coding method based on differences of discrete cosine transform (DCT) coefficients of overlapped angular patches from normalized iris images. Th...
Donald M. Monro, Soumyadip Rakshit, Dexin Zhang
ICIP
2006
IEEE
14 years 9 months ago
Efficient Object-Based Video Inpainting
Video inpainting is the process of repairing missing regions (holes) in videos. Most automatic techniques are computationally intensive and unable to repair large holes. To tackle...
Sen-Ching S. Cheung, Jian Zhao, M. Vijay Venkatesh
GRAPHICSINTERFACE
2003
13 years 9 months ago
Silhouette-Based 3D Face Shape Recovery
The creation of realistic 3D face models is still a fundamental problem in computer graphics. In this paper we present a novel method to obtain the 3D shape of an arbitrary human ...
Jinho Lee, Baback Moghaddam, Hanspeter Pfister, Ra...