Sciweavers

180 search results - page 15 / 36
» Learning to segment from a few well-selected training images
Sort
View
VIP
2003
13 years 10 months ago
Using Dual Cascading Learning Frameworks for Image Indexing
To bridge the semantic gap in content-based image retrieval, detecting meaningful visual entities (e.g. faces, sky, foliage, buildings etc) in image content and classifying images...
Joo-Hwee Lim, Jesse S. Jin
ICML
2005
IEEE
14 years 9 months ago
Variational Bayesian image modelling
We present a variational Bayesian framework for performing inference, density estimation and model selection in a special class of graphical models--Hidden Markov Random Fields (H...
Li Cheng, Feng Jiao, Dale Schuurmans, Shaojun Wang
DAS
2010
Springer
13 years 10 months ago
Overlapped text segmentation using Markov random field and aggregation
Separating machine printed text and handwriting from overlapping text is a challenging problem in the document analysis field and no reliable algorithms have been developed thus f...
Xujun Peng, Srirangaraj Setlur, Venu Govindaraju, ...
ICIP
2008
IEEE
14 years 10 months ago
Supervised image segmentation via ground truth decomposition
This paper proposes a data driven image segmentation algorithm, based on decomposing the target output (ground truth). Classical pixel labeling methods utilize machine learning al...
Ilya Levner, Russell Greiner, Hong Zhang
ICCV
2003
IEEE
14 years 10 months ago
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires mode...
Fei-Fei Li 0002, Robert Fergus, Pietro Perona