One way to decrease this time is to divide the fingerprint database into different subclasses based on specific properties, such that only a part of the fingerprints needs to be considered for matching. Embedded fingerprint systems supporting instant identification or verification are increasingly used, and the computation time for these processes is thus an important research field. The current work in this field concentrates on reducing the computation time for feature extraction and matching. There is nevertheless a huge amount of work still to be done. Due to the ever-growing capabilities of computers and great achievements in research, the recognition rate has improved significantly. Introduction The first Automatic Fingerprint Identification System (AFIS) was developed in 1991, and since then, there has been an enormous progress in the field. The matching time is estimated to decrease with a factor of about 3.7 compared to a brute force approach.ฤก. The classification rate of both systems is only differing marginally.A benchmark test has been done for both systems. The classification rate has been estimated to about 87.0 % and 88.8% of unseen fingerprints for SVM and MLP classification respectively. Two different classification regimes are used to train the systems to do correct classification. The given fingerprint database is decomposed into four different subclasses. The fingerprint patterns generated are based on minutiae extraction from a thinned fingerprint image. Automatic Fingerprint Identification Systems (AFIS) are widely used today, and it is therefore necessary to find a classification system that is less time-consuming. For classification, a Support Vector Machine (SVM) and a Multi-Layered Perceptron (MLP) network are described and used. In this work a hybrid technique for classification of fingerprint identification has been developed to decrease the matching time.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |