Abstract | ||
---|---|---|
This paper introduces new methodologies for reliably identifying writers of Arabic historical manuscripts. We propose an approach that transforms key point-based features, such as SIFT, into a global form that captures high-level characteristics of writing styles. We suggest a modification for a common local feature, the contour direction feature, and show the contribution of combining local and global features for writer identification. Our work also presents a novel algorithm that determines the number of writers involved in writing a given manuscript. The experimental study confirms the significant improvement in this algorithm on writer identification once applied to historical manuscripts. Comprehensive experiments using different features and classification schemes demonstrate the vitality of the suggested methodologies for reliable writer identification. The presented techniques were evaluated on both historical and modern documents where the suggested features yielded very promising results with respect to state-of-the-art features. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/s10032-017-0289-3 | IJDAR |
Keywords | Field | DocType |
Writer identification,Writer retrieval,Key point-based features,Contour-based features,Supervised learning,Hierarchical clustering,Classification | Hierarchical clustering,Scale-invariant feature transform,Arabic,Computer science,Classification scheme,Writing style,Supervised learning,Natural language processing,Artificial intelligence | Journal |
Volume | Issue | ISSN |
20 | 3 | 1433-2833 |
Citations | PageRank | References |
5 | 0.45 | 29 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abedelkadir Asi | 1 | 94 | 5.75 |
Alaa Abdalhaleem | 2 | 5 | 0.79 |
Daniel Fecker | 3 | 6 | 1.82 |
Volker Märgner | 4 | 295 | 29.02 |
Jihad El-sana | 5 | 922 | 70.99 |