Fingerprint Image Enhancement: Algorithm and Performance Evaluation

Dept. of Comput. Sci., Michigan State Univ., East Lansing, MI
IEEE Transactions on Pattern Analysis and Machine Intelligence (Impact Factor: 5.78). 09/1998; 20(8):777 - 789. DOI: 10.1109/34.709565
Source: CiteSeer


In order to ensure that the performance of an automatic
fingerprint identification/verification system will be robust with
respect to the quality of input fingerprint images, it is essential to
incorporate a fingerprint enhancement algorithm in the minutiae
extraction module. We present a fast fingerprint enhancement algorithm,
which can adaptively improve the clarity of ridge and valley structures
of input fingerprint images based on the estimated local ridge
orientation and frequency. We have evaluated the performance of the
image enhancement algorithm using the goodness index of the extracted
minutiae and the accuracy of an online fingerprint verification system.
Experimental results show that incorporating the enhancement algorithm
improves both the goodness index and the verification accuracy

Download full-text


Available from: Lin Hong, Nov 24, 2014
  • Source
    • "As opposed to human fingerprints, the frequency of the annual ring pattern is strongly varying. Similar as in our previous works (Schraml et al., 2014, 2015a) enhancement is based on the fingerprint enhancement approach presented by Hong et al. (1998). In Schraml et al. (2015a) we showed that a slight variation of the procedure utilized in Schraml et al. (2014) further improves the biometric system performance and is thus also used in this work. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Log traceability in the timber based industries is a basic requirement to fulfil economical, social and legal requirements. This work introduces biometric log recognition using digital log end images and explores the robustness to a set of log end cross-section (CS) variations. In order to investigate longitudinal and surface CS variations three tree logs were sliced and captured in different sessions. A texture feature-based technique well known from fingerprint recognition is adopted to compute and match biometric templates of CS images captured from log ends. In the experimental evaluation insights and constraints on the general applicability and robustness of log end biometrics to identify logs in an industrial application are presented. Results for different identification performance scenarios indicate that the matching procedure which is based on annual ring pattern and shape information is very robust to log length cutting using different cutting tools. The findings of this study are a further step towards the development of a biometric log recognition system.
    Full-text · Article · Nov 2015 · Computers and Electronics in Agriculture
  • Source
    • "Hong et. al. [2] have an evergreen paper dealing with fingerprint enhancements, orientation using ridge alignments and also recovery of poor images. On a similar note, Jea and Govindaraju [3] have devised an algorithm for matching partial or low quality prints utilizing a neural network. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Fingerprints are one of the oldest and most widely used biometric security measures. Rapid advances in Computer Science and digital Image Processing have made it possible to design various Automatic Fingerprint Identification Systems (AFIS) which can compare certain features of an input fingerprint image with a series of template images stored in a database and find a match. This paper deals with the extraction of certain specific features from a fingerprint, called minutiae. Since low quality images tend to generate multiple false minutiae, a method has been included to detect and remove such false minutiae. Fingerprint matching is performed by matching the number and type of the minutiae. The false minutiae removal process helps to reduce the computational complexity and improve the accuracy of the match.
    Full-text · Article · Oct 2015 · International Journal of Advanced Research in Computer Science
  • Source
    • "These gaps establish reference points for the computation of the Region Of Interest (ROI) by detecting the boundary of the hand shape and the center from a transofrmed binary image [21]. Then a normalization is applied in order to have a specific mean and variance for all images [7]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Most of the existing techniques for palmprint recognition are based on metrics that evaluate the distance between a pair of features. These metrics are typically based on static functions. In this paper we propose a new technique for palmprint recognition based on a dynamical system approach, focusing on preliminary experimental results. The essential idea is that the procedure iteratively eliminates points in both images to be compared which do not have enough close neighboring points in the image itself and in the comparison image. As a result of the iteration, in each image the surviving points are those having enough neighboring points in the comparison image. Our preliminary experimental results show that the proposed dynamic algorithm is competitive and slightly outperforms some state-of-the-art methods by achieving a higher genuine acceptance rate.
    Full-text · Conference Paper · Sep 2015
Show more