Abstract | ||
---|---|---|
This paper presents an approach to text line extraction in handwritten document images which combines local and global techniques. We propose a graph-based technique to detect touching and proximity errors that are common with handwritten text lines. In a refinement step, we use Expectation-Maximization (EM) to iteratively split the error segments to obtain correct text-lines. We show improvement in accuracies using our correction method on datasets of Arabic document images. Results on a set of artificially generated proximity images show that the method is effective for handling touching errors in handwritten document images. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICDAR.2011.31 | Document Analysis and Recognition |
Keywords | Field | DocType |
text line extraction,proximity error,handwritten text line,error segment,touching error,touching components,arabic document image,correct text-lines,handwritten document image,handwritten textlines,correction method,proximity image,natural language processing,arabic,least squares approximation,accuracy,text analysis,estimation,clustering algorithms,graph theory,feature extraction,image segmentation | Graph theory,Computer vision,Graph,Pattern recognition,Arabic,Document image processing,Segmentation,Computer science,Image segmentation,Feature extraction,Artificial intelligence,Cluster analysis | Conference |
ISSN | ISBN | Citations |
1520-5363 E-ISBN : 978-0-7695-4520-2 | 978-0-7695-4520-2 | 8 |
PageRank | References | Authors |
0.47 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jayant Kumar | 1 | 173 | 11.11 |
Le Kang | 2 | 306 | 9.32 |
David Doermann | 3 | 4313 | 312.70 |
Wael Abd-Almageed | 4 | 248 | 24.52 |