A review of fingerprint image enhancement methods

Heikki Ailisto, Mikko Lindholm, Pauli Tikkanen

    Research output: Contribution to journalArticleScientificpeer-review

    17 Citations (Scopus)

    Abstract


    Automatic fingerprint identification methods have become the most widely used technology in rapidly growing bioidentification applications. In this paper, different image enhancement approaches presented in the scientific literature are reviewed. Fingerprint verification can be divided into image acquisition, enhancement, feature extraction and matching steps. The enhancement step is needed to improve image quality prior to feature extraction. By far the most common approach relies on the filtering of the fingerprint images with filters adapted to local ridge orientation, but alternative approaches based on Fourier domain processing, direct ridge following and global features also exist. Methods of comparing the performance of enhancement methods are discussed. An example of the performance of different methods is given. Conclusions are made regarding the importance of effective enhancement, especially for noisy or low quality images.
    Original languageEnglish
    Pages (from-to)401-424
    JournalInternational journal of image and graphics
    Volume3
    Issue number3
    DOIs
    Publication statusPublished - 2003
    MoE publication typeA1 Journal article-refereed

    Keywords

    • biometrics
    • fingerprint
    • image processing
    • filtering
    • enhancement
    • feature extraction

    Fingerprint

    Dive into the research topics of 'A review of fingerprint image enhancement methods'. Together they form a unique fingerprint.

    Cite this