Sciweavers

382 search results - page 64 / 77
» Using Maximum Entropy for Automatic Image Annotation
Sort
View
IJCV
2000
164views more  IJCV 2000»
13 years 7 months ago
Probabilistic Modeling and Recognition of 3-D Objects
This paper introduces a uniform statistical framework for both 3-D and 2-D object recognition using intensity images as input data. The theoretical part provides a mathematical too...
Joachim Hornegger, Heinrich Niemann
ECCV
2010
Springer
13 years 10 months ago
Avoiding confusing features in place recognition
We seek to recognize the place depicted in a query image using a database of “street side” images annotated with geolocation information. This is a challenging task due to chan...
ICPR
2000
IEEE
14 years 9 months ago
Simultaneous Highlighting of Paper and Electronic Documents
The ability to automatically record the marks applied to paper documents on their electronic originals would preserve the information represented by those annotations. Users could...
Jonathan J. Hull, Dar-Shyang Lee
CVPR
2007
IEEE
14 years 10 months ago
Iterative MAP and ML Estimations for Image Segmentation
Image segmentation plays an important role in computer vision and image analysis. In this paper, the segmentation problem is formulated as a labeling problem under a probability m...
Shifeng Chen, Liangliang Cao, Jianzhuang Liu, Xiao...
CVPR
2008
IEEE
14 years 10 months ago
Edge preserving spatially varying mixtures for image segmentation
A new hierarchical Bayesian model is proposed for image segmentation based on Gaussian mixture models (GMM) with a prior enforcing spatial smoothness. According to this prior, the...
Giorgos Sfikas, Christophoros Nikou, Nikolas P. Ga...