Sciweavers

904 search results - page 88 / 181
» Object Recognition by Integrating Multiple Image Segmentatio...
Sort
View
CVPR
2009
IEEE
15 years 3 months ago
Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers
Most modern computer vision systems for high-level tasks, such as image classification, object recognition and segmentation, are based on learning algorithms that are able to se...
Peter V. Gehler, Sebastian Nowozin
ECCV
1992
Springer
13 years 12 months ago
Data and Model-Driven Selection using Color Regions
A key problem in model-based object recognition is selection, namely, the problem of determining which regions in the image are likely to come from a single object. In this paper w...
Tanveer Fathima Syeda-Mahmood
ICCV
1995
IEEE
13 years 11 months ago
Recognition Using Region Correspondences
Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estima...
Ronen Basri, David W. Jacobs
ICDAR
2009
IEEE
13 years 5 months ago
Low-Resolution Character Recognition by Video-Based Super-Resolution
In this paper, we propose a method for recognizing lowresolution characters using a super-resolution technique. Although portable digital cameras can be used for camerabased chara...
Ataru Ohkura, Daisuke Deguchi, Tomokazu Takahashi,...
GIS
2007
ACM
14 years 9 months ago
Linear feature extraction using perceptual grouping and graph-cuts
In this paper we present a novel system for the detection and extraction of road map information from high-resolution satellite imagery. Uniquely, the proposed system is an integr...
Charalambos Poullis, Suya You, Ulrich Neumann