Fingerprint Enhancement by Shape Adaptation of Scale-Space Operators with Automatic Scale-Selection

Andrés Almansa and Tony Lindeberg

Technical Report TRITA-NA/P--98/03--SE.

Earlier version in J. Sporring, M. Nielsen, L. Florack and P. Johansen (eds.) (1997) Gaussian Scale-Space Theory: Proc. PhD School on Scale-Space Theory, (Copenhagen, Denmark, May 1996). Kluwer Academic Publishers.

Revised and condensed version available as Technical report ISRN KTH/NA/R--99/01--SE, to appear in IEEE Transactions on Image Processing.

Abstract

This work presents a novel technique for preprocessing fingerprint images. The method is based on the measurements of second moment descriptors and shape adaptation of scale-space operators with automatic scale selection (Lindeberg 1994). This procedure, which has been successfully used in the context of shape-from-texture and shape from disparity gradients, has several advantages when applied to fingerprint image enhancement, as observed by (Weickert 1995). For example, it is capable of joining interrupted ridges, and enforces continuity of their directional fields.

In this work, these abovementioned general ideas are applied and extended in the following ways: Two methods for estimating local ridge width are explored and tuned to the problem of fingerprint enhancement. A ridgeness measure is defined, which reflects how well the local image structure agrees with a qualitative ridge model. This information is used for guiding a scale-selection mechanism, and for spreading the results of shape adaptation into noisy areas.

The combined approach makes it possible to resolve fine scale structures in clear areas while reducing the risk of enhancing noise in blurred or fragmented areas. To a large extent, the scheme has the desirable property of joining interrupted lines without destroying essential singularities such as branching points. Thus, the result is a reliable and adaptively detailed estimate of the ridge orientation field and ridge width, as well as a smoothed grey-level version of the input image.

A detailed experimental evaluation is presented, including a comparison with other techniques. We propose that the techniques presented provide mechanisms of interest to developers of automatic fingerprint identification systems.

Contents

• Frontmatter
• Section 1: Introduction
• Section 2: Previous work on fingerprint image enhancement and feature detection
• Section 3: Methodology
• Section 4: Shape adapted smoothing
• Section 5: Automatic scale selection
• Section 6: Objective evaluation
• Section 7: Relations to previous work on non-linear diffusion and fingerprint analysis
• Section 8: Summary and discussion
• Section 9: Future extensions and improvements
• Section 10: Acknowledgments
• Appendix A: Algorithmic description of the composed shape adaptation scheme
• Appendix B: Numerical Implementation
• Appendix C: Anisotropic scale selection
• Appendix D: Data sets and experimental results
• Backmatter

Printing instructions:

The report is available as a set of 8 (gzip) compressed PostScript files, as follows:

• Part 1 (1.7 Mbytes) contains the frontmatter (titlepage, abstract, and table of contents) and sections 1-4
• Part 2a (2.4 Mbytes) contains sections 5-5.5
• Part 2b (1.0 Mbytes) contains sections 5.6 to the end of section 5
• Part 3 (68 Kbytes) contains sections 6-10
• Part 4 (87 Kbytes) contains appendices A-C
• Part 5 (6.5 Mbytes) contains appendix D
• Part 6 (17 Kbytes) contains the backmatter (references)
• Only appendix D (6.5 Mbytes) and part of section 6 (17 Kbytes) require a color printer.

The text is typeset for double-side printing in A4 paper. For a good reproduction of the figures, a minimum printer resolution of 600 dpi is recommended.

Background material:

(Review paper on scale-space representation and automatic scale selection) (TR on feature detection with automatic scale selection) (Article on shape adaptation) (Monograph on scale-space theory) (Other publications on scale-space theory) (Encyclopedia entry on scale-space theory)