Fingerprint Identification Based on Mopso in SVM
Chia Shing Hu, Chia Shing Hu · Applied Mechanics and Materials · 2013
Abstract. The problem of fingerprint classification is discussed for many years. Support Vector Machine (SVM) is a traditional artificial intelligence algorithm developed for dealing classification problems. In this paper, we used the idea of multi-objective optimization to transform SVM into a new form, since the core concept of SVM is built up on a single optimization equation, and some parameters for this algorithm still need user to make tons of experiment to determine. Our algorithm has successfully proved that user do not need to make experiment to determine the penalty parameter C. NIST-4 database is used to assess our proposed algorithm. The experiment results show our method can get good classification results.