Sciweavers

1284 search results - page 10 / 257
» A novel local feature descriptor for image matching
Sort
View
ICMCS
2008
IEEE
131views Multimedia» more  ICMCS 2008»
15 years 4 months ago
A novel contextual descriptors for category recognition
In this paper, we propose a novel contextual descriptor which combines the contextual information and local appearance. Based on Gibbs distribution, a local descriptor is designed...
Yi Ouyang, Ming Tang, Jian Cheng, Jinqiao Wang, Ha...
AVBPA
2003
Springer
158views Biometrics» more  AVBPA 2003»
15 years 3 months ago
A Novel Method to Extract Features for Iris Recognition System
In general, the iris recognition systems have used the wavelet transform as feature extraction techniques. Since the wavelet transform does not have the shift-invariant property, t...
Seung-In Noh, Kwanghyuk Bae, Yeunggyu Park, Jaihie...
BMVC
2002
15 years 6 days ago
Invariant Features from Interest Point Groups
This paper approaches the problem of finding correspondences between images in which there are large changes in viewpoint, scale and illumination. Recent work has shown that scale...
Matthew Brown, David G. Lowe
ICRA
2005
IEEE
167views Robotics» more  ICRA 2005»
15 years 3 months ago
Localization for Mobile Robots using Panoramic Vision, Local Features and Particle Filter
— In this paper we present a vision-based approach to self-localization that uses a novel scheme to integrate featurebased matching of panoramic images with Monte Carlo localizat...
Henrik Andreasson, André Treptow, Tom Ducke...
CIVR
2008
Springer
279views Image Analysis» more  CIVR 2008»
14 years 11 months ago
Semi-supervised learning of object categories from paired local features
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
Wen Wu, Jie Yang