Magnetic energy-based feature extraction for low-quality fingerprint images

被引:26
作者
Hassanat, Ahmad B. A. [1 ]
Prasath, V. B. Surya [3 ,4 ,5 ]
Al-kasassbeh, Mouhammd [1 ]
Tarawneh, Ahmad S. [1 ,2 ]
Al-shamailh, Ahmad J. [1 ]
机构
[1] Mutah Univ, Dept Informat Technol, Al Karak, Jordan
[2] Eotvos Lorand Univ, Dept Algorithms & Their Applicat, Budapest, Hungary
[3] Univ Missouri Columbia, Computat Imaging & VisAnal CIVA Lab, Dept Comp Sci, Columbia, MO 65211 USA
[4] Cincinnati Childrens Hosp Med Ctr, Div Biomed Informat, Cincinnati, OH 45229 USA
[5] Univ Cincinnati, Dept Biomed Informat, Coll Med, Cincinnati, OH 45220 USA
关键词
Fingerprint recognition; Low-quality images; Feature extraction; Magnetic energy; Smartphone camera; VALIDATION; MINUTIAE;
D O I
10.1007/s11760-018-1302-0
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In fingerprint recognition systems, feature extraction is an important part because of its impact on the final performance of the overall system, particularly, in the case of low-quality images, which poses significant challenges to traditional fingerprint feature extraction methods. In this work, we make two major contributions: First, a novel feature extraction method for low-quality fingerprints images is proposed, which mimics the magnetic energy when attracting iron fillings, and this method is based on image energies attracting uniformly distributed points to form the final features that can describe a fingerprint. Second, we created a new low-quality fingerprints image database to evaluate the proposed method. We used a mobile phone camera to capture the fingerprints of 136 different persons, with five samples for each to obtain 680 fingerprint images in total. To match the computed features, we used the dynamic time warping and evaluated the performance of our system based on k-nearest neighbor classifier. Further, we represent the features using their probability density functions to evaluate the method using some other classifiers. The highest identification accuracy recorded by several experiments reached 95.11% using our in-house database. The experimental results show that the proposed method can be used as a general feature extraction method for other applications.
引用
收藏
页码:1471 / 1478
页数:8
相关论文
共 30 条
  • [1] [Anonymous], 2009, SIGKDD Explorations, DOI DOI 10.1145/1656274.1656278
  • [2] [Anonymous], CLASSIFICATION BIOAP
  • [3] [Anonymous], 2017, INTELLIGENT TECHNIQU
  • [4] [Anonymous], INT C DAT MAN ICDM
  • [5] Blurred fingerprint image enhancement: algorithm analysis and performance evaluation
    Arif, Annatoma
    Li, Tuo
    Cheng, Chi-Hao
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2018, 12 (04) : 767 - 774
  • [6] Efficient leave-one-out cross-validation of kernel Fisher discriminant classifiers
    Cawley, GC
    Talbot, NLC
    [J]. PATTERN RECOGNITION, 2003, 36 (11) : 2585 - 2592
  • [7] A survey of fingerprint classification Part I: Taxonomies on feature extraction methods and learning models
    Galar, Mikel
    Derrac, Joaquin
    Peralta, Daniel
    Triguero, Isaac
    Paternain, Daniel
    Lopez-Molina, Carlos
    Garcia, Salvador
    Benitez, Jose M.
    Pagola, Miguel
    Barrenechea, Edurne
    Bustince, Humberto
    Herrera, Francisco
    [J]. KNOWLEDGE-BASED SYSTEMS, 2015, 81 : 76 - 97
  • [8] New mobile phone and webcam hand images databases for personal authentication and identification
    Hassanat, Ahmad
    Al-Awadi, Mouhammd
    EmanBtoush
    Al-Btoush, Amani
    Esra'aAlhasanat
    GhadaAltarawneh
    [J]. 6TH INTERNATIONAL CONFERENCE ON APPLIED HUMAN FACTORS AND ERGONOMICS (AHFE 2015) AND THE AFFILIATED CONFERENCES, AHFE 2015, 2015, 3 : 4060 - 4067
  • [9] Hassanat AB, 2017, INT J BIOMETRICS, V9, P347, DOI 10.1504/IJBM.2017.088251
  • [10] Digital camera based fingerprint recognition
    Hiew, B. Y.
    Teoh, Andrew B. J.
    Pang, Y. H.
    [J]. ICT-MICC: 2007 IEEE INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND MALAYSIA INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1 AND 2, PROCEEDINGS, 2007, : 676 - +