A survey of fingerprint classification Part I: Taxonomies on feature extraction methods and learning models

Abstract

Orientation map 35 Singular points 36 3 7 a b s t r a c t 38 This paper reviews the fingerprint classification literature looking at the problem from a double perspec-39 tive. We first deal with feature extraction methods, including the different models considered for singular 40 point detection and for orientation map extraction. Then, we focus on the different learning models con-41 sidered to build the classifiers used to label new fingerprints. Taxonomies and classifications for the fea-42 ture extraction, singular point detection, orientation extraction and learning methods are presented. A 43 critical view of the existing literature have led us to present a discussion on the existing methods and 44 their drawbacks such as difficulty in their reimplementation, lack of details or major differences in their 45 evaluations procedures. On this account, an experimental analysis of the most relevant methods is car-46 ried out in the second part of this paper, and a new method based on their combination is presented.47

Analisis dan Implementasi Metode Gabor Filter dan Support Vector Machine pada Klasifikasi Sidik Jari

“…Sidik jari manusia memiliki sifat yang tidak akan mengalami perubahan bentuk sejak lahir sehingga memudahkan identifikasi. Klasifikasi sidik jari sudah menjadi perbincangan menarik sejak tahun 1975 dan terus berkembang hingga sekarang [3]. Klasifikasi merupakan pemberian label kelas terhadap suatu benda berdasarkan masukan berupa karakter dari fitur benda baik itu secara numerik maupun nominal.…”

DPD-DFF: A dual phase distributed scheme with double fingerprint fusion for fast and accurate identification in large databases

“…Other approaches reduce the penetration rate in the database by using a previous classification or indexing step [31,32,33,34]. Nevertheless, in large databases this step may become the bottleneck, and the size of the subsets can become too large.…”

A Human Identity Recognition System Based on Kinect Skeletal Tracking and ANN Classifier

“…Biometric recognition [1] [9] is developing in rise with the favorable security, validity and irreplaceability. In these systems, physiological traits, such as fingerprint [2], face recognition [4], iris recognition [7], retina scan, and behavioral traits, such as typing rhythm, key stroke, pattern and handwriting, have been intensively studied and developed to solve security problem inherent in traditional personal recognition methods. In this paper, by using Kinect skeletal tracking technology [6] developed by Microsoft, we proposed a novel method for human identity recognition based on the structure of bones which has some advantages: more acceptable by the users since it is more convenient without any specific requirements; better anti-falsification due to the unique of human's bone organization, it is hard to be falsified or stolen; easier to carry on and with less risk of loss, because the bone organization is human's intrinsic properties.…”