469 search results - page 64 / 94 » A Robust Split-and-Merge Text Segmentation Approach for Imag... |
104
click to vote
PAMI
2008
14 years 9 months ago
2008
Although it has been studied for years by the computer vision and machine learning communities, image annotation is still far from practical. In this paper, we propose a novel atte...
107
Voted
ECCV
2008
Springer
15 years 11 months ago
2008
Springer
Developing effective content recognition methods for diverse imagery continues to challenge computer vision researchers. We present a new approach for document image content catego...
ICDAR
2011
IEEE
13 years 9 months ago
2011
IEEE
—Retrieval from Hindi document image collections is a challenging task. This is partly due to the complexity of the script, which has more than 800 unique ligatures. In addition,...
CVIU
2007
14 years 9 months ago
2007
We investigate the problem of automatically creating 3D models of man-made environments that we represent as collections of textured planes. A typical approach is to automatically...
128
click to vote
PAMI
2008
14 years 9 months ago
2008
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and po...