Cursive signature extraction and verification

This paper presents a new approach for document image decomposition and verification based on connected component analysis and geometric properties of labeled regions. The database contains document images with Persian/Arabic text combined with English text, headlines, ruling lines, trademarks and cursive signatures. In particular, Persian/Arabic signature extraction is investigated using special characteristics of the signature that is fairly different from English signatures. A set of efficient, invariant and compact features is extracted for verification purposes using spatial partitioning of the signature region. Comparative results show the robustness of the proposed method.