Abstract | ||
---|---|---|
A hierarchical framework for document segmentation is proposed as an optimization problem. The model incorporates the dependencies between various levels of the hierarchy unlike traditional document segmentation algorithms. This framework is applied to learn the parameters of the document segmentation algorithm using optimization methods like gradient descent and Q-learning. The novelty of our approach lies in learning the segmentation parameters in the absence of groundtruth. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11590316_73 | PReMI |
Keywords | Field | DocType |
segment document image,various level,optimization problem,segmentation parameter,hierarchical framework,traditional document segmentation algorithm,gradient descent,optimization method,document segmentation,document segmentation algorithm,image segmentation,top down,bottom up,digital library | Data mining,Scale-space segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Optimization problem,Gradient descent,Pattern recognition,Segmentation,Document processing,Document layout analysis,Machine learning | Conference |
Volume | ISSN | ISBN |
3776 | 0302-9743 | 3-540-30506-8 |
Citations | PageRank | References |
3 | 0.47 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
S. Kumar | 1 | 36 | 4.04 |
Anoop M. Namboodiri | 2 | 255 | 26.36 |
C. V. Jawahar | 3 | 1700 | 148.58 |