Writer Independent Offline Signature Recognition Using Ensemble Learning

• DOI: 10.48550/arxiv.1901.06494
• Publication Date: 2019-01-01
• Authors: Sourya Dipta Das; Himanshu Ladia; Vaibhav Kumar; Shivansh Mishra
• Keywords: Signature (topology); Ensemble Learning; Online and offline

The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, dynamic information writing process is lost, and it difficult to design good feature extractors that can distinguish genuine signatures skilled forgeries. This verification task even harder writer independent scenarios which undeniably fiscal for realistic cases. this paper, we have proposed Ensemble model writer, with Deep learning. We used two CNNs extraction, after RGBT classification & Stacking generate final prediction vector. done extensive experiments on various datasets from sources maintain a variance dataset. achieved state art performance datasets.