Handwritten signature verification using the quad-tree histogram of templates and a Support Vector-based artificial immune classification

作者：

Highlights：

• A novel system is proposed for solving the automatic off-line handwritten signature verification.

• A quad-tree implementation of Histogram Of Templates is proposed for signature characterization.

• Artificial Immune Recognition System is used for handwritten signature verification.

• Improved implementation of Artificial Immune Recognition System with a Support Vector decision is proposed.

• Results obtained on three publicly available datasets reveal the effectiveness of the proposed system.

摘要

•A novel system is proposed for solving the automatic off-line handwritten signature verification.•A quad-tree implementation of Histogram Of Templates is proposed for signature characterization.•Artificial Immune Recognition System is used for handwritten signature verification.•Improved implementation of Artificial Immune Recognition System with a Support Vector decision is proposed.•Results obtained on three publicly available datasets reveal the effectiveness of the proposed system.

论文关键词：Artificial Immune Recognition System,Handwritten signature verification,Histogram Of Templates,Support Vector decision

论文评审过程：Received 5 September 2016, Revised 15 June 2017, Accepted 28 August 2017, Available online 7 September 2017, Version of Record 22 September 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2017.08.004