Sciweavers

357 search results - page 22 / 72
» Unsupervised Multiscale Image Segmentation
Sort
View
DICTA
2003
15 years 1 months ago
False-Peaks-Avoiding Mean Shift Method for Unsupervised Peak-Valley Sliding Image Segmentation
The mean shift (MS) algorithm is sensitive to local peaks. In this paper, we show both empirically and analytically that when using sample data, the reconstructed PDF may have fals...
Hanzi Wang, David Suter
TIP
2002
179views more  TIP 2002»
14 years 11 months ago
Unsupervised image classification, segmentation, and enhancement using ICA mixture models
An unsupervised classification algorithm is derived by modeling observed data as a mixture of several mutually exclusive classes that are each described by linear combinations of i...
Te-Won Lee, Michael S. Lewicki
CVPR
2007
IEEE
16 years 1 months ago
Modelling Objects using Distribution and Topology of Multiscale Region Pairs
We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this ...
Himanshu Arora, Narendra Ahuja
TIP
2010
87views more  TIP 2010»
14 years 10 months ago
A Nonconservative Flow Field for Robust Variational Image Segmentation
—We introduce a robust image segmentation method based on a variational formulation using edge flow vectors. We demonstrate the nonconservative nature of this flow field, a fe...
Pratim Ghosh, Luca Bertelli, Baris Sumengen, B. S....
CVPR
2010
IEEE
1341views Computer Vision» more  CVPR 2010»
15 years 8 months ago
Unsupervised Detection and Segmentation of Identical Objects
We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or model-test settings betwe...
Minsu Cho (Seoul National University), Young Min S...