Multi-script Writer Identification Optimized with Retrieval Mechanism

Abstract

Identifying the writer of a handwritten document has been an active research area over the last few years with applications in biometrics, forensics, smart meeting rooms and historical document analysis. In this paper, we present a new writer identification system based on a retrieval mechanism. Texture based edge-hinge and run-length features are used to characterize the writing style of an individual. The effectiveness of the proposed system is evaluated on a total of 1583 writing samples in Arabic, German, English, French, and Greek from two different databases. The experimental evaluations reveal that reducing the search space using a writer retrieval mechanism prior to identification improves the identification rates.