A new enhancement of fingerprint classification for the damaged fingerprint with adaptive features

• Main Authors: Josphineleela, R., Ramakrishnan, M., Gunasekaran,
• Format: Conference or Workshop Item
• Language: English
• Published: 2009
• Subjects: QA76 Computer software
• Online Access: http://repo.uum.edu.my/13533/1/PID216.pdf; http://repo.uum.edu.my/13533/; http://www.icoci.cms.net.my
• Institution: Universiti Utara Malaysia

In this paper, we propose an new enhancement of the classification for damaged fingerprint database.It is based on the fact that damaged fingerprint image is composed of regular texture regions that can be successfully represents by co-occurrence matrices.So, we first extract the features based on certain characteristics and then we use these features to train a neural network for classifying fingerprints into five classes.The obtained results compared with existing approaches demonstrate the superior performance of our new enhancement.