Sciweavers

2643 search results - page 107 / 529
» A fast feature extraction method
Sort
View
ICPR
2008
IEEE
14 years 2 months ago
GA based feature generation for training cascade object detector
Viola et al. have introduced a fast object detection scheme based on a boosted cascade of haar-like features. In this paper, we introduce a novel ternary feature that enriches the...
Qian Chen, Haiyuan Wu, Toshikazu Wada, Kazuyuki Ma...
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
15 years 3 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
ICCV
2007
IEEE
14 years 10 months ago
A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting
An interactive framework for soft segmentation and matting of natural images and videos is presented in this paper. The proposed technique is based on the optimal, linear time, co...
Xue Bai, Guillermo Sapiro
ICMCS
2009
IEEE
130views Multimedia» more  ICMCS 2009»
13 years 5 months ago
Fast multi-reference motion estimation via statistical learning for H.264/AVC
In the H.264/AVC coding standard, motion estimation (ME) is allowed to use multiple reference frames to make full use of reducing temporal redundancy in a video sequence. Although...
Chen-Kuo Chiang, Shang-Hong Lai
IVC
2007
191views more  IVC 2007»
13 years 7 months ago
Rotation-invariant and scale-invariant Gabor features for texture image retrieval
Conventional Gabor representation and its extracted features often yield a fairly poor performance in retrieving the rotated and scaled versions of the texture image under query. ...
Ju Han, Kai-Kuang Ma