A framework of artificial immune system in writer identification

• Main Authors: Muda, Azah Kamilah, Shamsuddin, Siti Mariyam
• Format: Conference or Workshop Item
• Language: English
• Published: 2005
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.utm.my/id/eprint/577/1/04.pdf; http://eprints.utm.my/id/eprint/577/

Artificial Immune Systems (AIS) is an emerging computer science technique which is inspired from biological process and has a nonlinear classification property along with biological property such as Negative Selection (NS). AIS has been proved as one of the mechanism that has a good potential in solving complex problem such as pattern recognition. Meanwhile, handwritten writer identification is one of the most popular areas of research in pattern recognition due to its immense potential on commercial perspective. Due to the importance and increasing interest in bio-inspired computing, this paper proposed AIS framework for writer identification. However, early findings on data iris and pendigits show that the proposed framework is convincing with an accuracy of more than 80.0% with various matching techniques.