810 search results - page 65 / 162 » Learning to Segment Document Images |
Publication
This study investigates variational image segmentation with an original data term, referred to as statistical overlap prior, which measures the conformity of overlap between the no...
TMI
1998
13 years 8 months ago
1998
Abstract— This paper reports a novel method for fully automated segmentation that is based on description of shape and its variation using point distribution models (PDM’s). An...
WACV
2007
IEEE
14 years 3 months ago
2007
IEEE
We present a method for the simultaneous detection and segmentation of objects from static images. We employ lowlevel contour features that enable us to learn the coarse object sh...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
Detecting and segmenting free-form objects from cluttered backgrounds is a challenging problem in computer vision. Signature detection in document images is one classic example an...
CORR
2010
Springer
13 years 9 months ago
2010
Springer
We propose a mid-level image segmentation framework that combines multiple figure-ground hypothesis (FG) constrained at different locations and scales, into interpretations that t...