Sciweavers

810 search results - page 30 / 162
» Learning to Segment Document Images
Sort
View
CVPR
2008
IEEE
16 years 1 months ago
Unsupervised estimation of segmentation quality using nonnegative factorization
We propose an unsupervised method for evaluating image segmentation. Common methods are typically based on evaluating smoothness within segments and contrast between them, and the...
Roman Sandler, Michael Lindenbaum
89
Voted
DAS
2008
Springer
15 years 1 months ago
Detecting Gradients in Text Images Using the Hough Transform
The use of gradients in text images is nowadays quite frequent. Existing segmentation methods encounter serious problems when it comes to modern text images where gradients might ...
Dimosthenis Karatzas
ISBI
2007
IEEE
15 years 6 months ago
Dynamic Texture Based Heart Localization and Segmentation in 4-D Cardiac Images
In this paper we present a dynamic texture based motion segmentation approach to address the challenging problem of heart localization and segmentation in 4D Spatio-temporal cardi...
Junzhou Huang, Xiaolei Huang, Dimitris N. Metaxas,...
ICDAR
2011
IEEE
13 years 11 months ago
BLSTM Neural Network Based Word Retrieval for Hindi Documents
—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,...
Raman Jain, Volkmar Frinken, C. V. Jawahar, Raghav...
IJCNN
2006
IEEE
15 years 5 months ago
Learning to Segment Any Random Vector
— We propose a method that takes observations of a random vector as input, and learns to segment each observation into two disjoint parts. We show how to use the internal coheren...
Aapo Hyvärinen, Jukka Perkiö