Auto Signature Verification Using Line Projection Features Combined With Different Classifiers and Selection Methods

Main Article Content

Mohammad Malkawi
Wail Mardini
Toqa Abu Zaitoun


: Signature verification plays a role in the commercial, legal and financial fields. The signature continues to be one of the most preferred types of authentication for many documents such as checks, credit card transaction receipts, and other legal documents. In this study, we propose a system for validating handwritten bank check signatures to determine whether the signature is original or forged. The proposed system includes several steps including improving the signature image quality, noise reduction, feature extraction, and analysis. The extracted features depend on the signature line and projection features. To verify signatures, different classification methods are used. The system is then trained with a set of signatures to demonstrate the validity of the proposed signature verification system. The experimental results show that the best accuracy of 100% was obtained by combining several classification methods.

Article Details

How to Cite
Malkawi, M., Mardini, W., & Abu Zaitoun, T. (2022). Auto Signature Verification Using Line Projection Features Combined With Different Classifiers and Selection Methods. International Journal of Communication Networks and Information Security (IJCNIS), 13(2). (Original work published August 26, 2021)
Research Articles
Author Biographies

Mohammad Malkawi, Jordan University of Science and Technology

Mohammad Isam Malkawi.   is experienced Computer Scientist and network architect who specializes in the  design  of  High-Throughput  Broadband Wireless Systems and Reliability, availability, and performance models for high productivity systems, FIVE NINES  end-to-end networks,  and wireless sensor  Neural/Fuzzy logic  system  for  analyzing human  emotion  and  detecting  current  human emotion.  He holds a PhD in Computer Engineering, University of Illinois at Urbana-Champaign in 1986 and MS in Computer Engineering, Yarmouk University, Jordan in 1983, BS in Computer Engineering, Tashkent University, Uzbekistan in1980.  He managed and architected scheduling and ranging algorithms for 802.11n and .11ac wireless networks. He has two patents disclosures (pending approval) 5 patents under consideration.

Wail Mardini, Jordan University of Science and Technology

is a professor of Computer Science at the computer science department at Jordan University of Science and Technology (JUST) in Jordan. Dr. Mardini received his Ph.D. degree in Computer Science from the University of Ottawa/Canada in 2006 and his Master's degree from the University of New Brunswick/Canada in 2001. Dr. Mardini is working at JUST since 2006. Moreover, he was the CS department chair during the academic years 2010/2011, 2011/2012, and 2019/2020 and the faculty vice-dean during the academic year 2012/2013. Dr. Mardini has many publications in the area of network survivability, wireless and wireless sensor networks, and optical‐wireless networks. He is currently working on Wireless Mesh Networks, Wireless Sensor Networks, Optical Network Survivability, WiMax Technology, Scheduling in Parallel Computing and Intrusion Detection in Database Techniques.

Toqa Abu Zaitoun, Jordan University of Science and Technology

StudentDepartment of Computer Science