Fingerprint Image Enhancement using Filtering Techniques

Abstract

E xtracting minutiae from fingerprint images is one of the most important steps in automatic fingerprint identification and classification. Minutiae are local discontinuities in the fingerprint pattern, mainly terminations and bifurcations. Most of the minutiae detection methods are based on image binarization while some others extract the minutiae directly from gray-scale images. In this work we compare these two approaches and propose two different methods for fingerprint ridge image enhancement. The first one is carried out using local histogram equalization, Wiener filtering, and image binarization. The second method uses a unique anisotropic filter for direct gray-scale enhancement. The results achieved are compared with those obtained through some other methods. Both methods show some improvement in the minutiae detection process in terms of time required and efficiency.

Effect of parameter values on fingerprint filtering

“…Filtered images of selected fingerprints based on parameters specified in Ref. [15,25,31] They exhibit similar parameters and characteristics with the one presented in the current study and these motivated their choice for comparative study. The results for the filtered images presented in Figures 7 and 8 are shown in Figure 9.…”

“…Filtered results based on parameters specified in the current study are presented in Figure 7 while Figure 8 shows the filtering results based on Gabor filter algorithms and values specified in Ref. [15,25,31] The filtering results for the current study presented in Figures 7(d), 7(e) and 7(f) show best performances in term of clarity of the ridges and orientation smoothening. Visual inspection of Figure 8 reveals several loss of connection among ridges which is attributed to insufficient filtering of the images.…”

“…Some popular fingerprint filtering algorithms are presented by the authors in Ref. [15,25,31] Figure 7. Filtered images of selected fingerprints based on specified parameters Figure 8.…”

“…The algorithm generates high numbered enhancement artefacts due to restriction of filtering to regions with high noise density and insufficient quality factors. The authors [25] proposed Wiener and anisotropic-based algorithms for fingerprint image filtering. Though the algorithms exhibit improvement over some existing algorithms in terms of speed and accuracy, they are only applicable to enhancement of gray-scale images.…”

Review of Hand Feature of Unimodal and Multimodal Biometric System

“…The result of the proposed method is compared with the conventional Otsu's thresholding method for binarization. [11] In paper [42] proposes two methods for fingerprint image enhancement. The first one is carried out using local histogram equalization, Wiener filtering, and image binarization, also using a unique anisotropic filter for direct greyscale enhancement.…”