Sciweavers

166 search results - page 21 / 34
» A Hybrid Learning Approach for Better Recognition of Visual ...
Sort
View
PRL
2006
121views more  PRL 2006»
13 years 7 months ago
Information-preserving hybrid data reduction based on fuzzy-rough techniques
Data reduction plays an important role in machine learning and pattern recognition with a high-dimensional data. In real-world applications data usually exists with hybrid formats...
Qinghua Hu, Daren Yu, Zongxia Xie
DICTA
2003
13 years 9 months ago
Learning Semantic Concepts from Visual Data Using Neural Networks
For content-based image retrieval techniques, query image is used to pick up and rank some relevant images from a database using some certain similarity metric. If semantic feature...
Xiaohang Ma, Dianhui Wang
ICRA
2010
IEEE
164views Robotics» more  ICRA 2010»
13 years 6 months ago
Boundary detection based on supervised learning
— Detecting the boundaries of objects is a key step in separating foreground objects from the background, which is useful for robotics and computer vision applications, such as o...
Kiho Kwak, Daniel F. Huber, Jeongsook Chae, Takeo ...
DPC
1996
192views more  DPC 1996»
13 years 9 months ago
Finding Pictures of Objects in Large Collections of Images
Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are st...
David A. Forsyth, Jitendra Malik, Thomas K. Leung,...
ICCV
2009
IEEE
1824views Computer Vision» more  ICCV 2009»
15 years 19 days ago
Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel
Common visual codebook generation methods used in a Bag of Visual words model, e.g. k-means or Gaussian Mixture Model, use the Euclidean distance to cluster features into visual...
Jianxin Wu, James M. Rehg