Enhanced Gray Scale Skeletonization of Fingerprint Ridges Using Parallel Algorithm

Thinning of fingerprint ridges plays a vital role in fingerprint identification systems as it simplifies the subsequent processing steps like fingerprint classification and feature extraction. In this paper, we analyze some of the parallel thinning algori

  • PDF / 2,051,491 Bytes
  • 10 Pages / 439.37 x 666.142 pts Page_size
  • 100 Downloads / 190 Views

DOWNLOAD

REPORT


Abstract. Thinning of fingerprint ridges plays a vital role in fingerprint identification systems as it simplifies the subsequent processing steps like fingerprint classification and feature extraction. In this paper, we analyze some of the parallel thinning algorithms and have proposed a methodology for skeletonization of fingerprint ridges directly on gray scale images as significant amount of information and features are lost during the binarization process. This algorithm is based on conditionally eroding the gray level ridges iteratively until a one pixel thick ridge is obtained. Refinement procedures have also been proposed to improve the quality of ridge skeleton. Experiments conducted on sample fingerprint images collected using an optical fingerprint Reader exhibit desirable features of the proposed approach. Keywords: Gray scale image algorithm · Iterative

1

· Fingerprint · Skeletonization · Parallel

Introduction

Automatic fingerprint recognition has received considerable attention over the past decades as fingerprint is one of the most popular and reliable methods used for personal identification. A fingerprint is composed of a pattern of interleaved ridges and valleys [1] as shown in Fig. 1. As fingerprint based applications are mostly real time, they require faster algorithms for processing. Hence it is useful to convert the original image data to a more compact representation to remove redundant information as much as possible and therefore fingerprint ridge skeletonization becomes an essential step in the recognition process for subsequent steps. Most fingerprint recognition systems are based on minutiae matching [1] (i.e.) ridge endings and ridge bifurcations and hence extraction of reliable minutiae relies heavily on the quality of the ridge skeleton. Ridge skeletons are obtained by the application of thinning reduction operator. The result of skeletonization using thinning algorithms should satisfy the following conditions [1]: 1. Preserve topological characteristics (i.e.) doesn’t cause disconnections or create holes. c Springer Nature Singapore Pte Ltd. 2017  K.C. Santosh et al. (Eds.): RTIP2R 2016, CCIS 709, pp. 440–449, 2017. DOI: 10.1007/978-981-10-4859-3 39

Gray Scale Fingerprint Ridge Skeletonization

441

Fig. 1. Ridges and valleys in a fingerprint image

2. Preserve geometry (i.e.) aligned to medial axis and retain original shape. 3. Single pixel wide lines and curves. 4. Preserve end points to sufficiently represent the ridge shape. Most of the proposed methods work on the binarized version of fingerprint images [3,4]. The methodology proposed in this paper for gray-scale skeletonization of fingerprint ridges is motivated by the consideration that a significant amount of information is lost during the binarization process. Though there are many thinning algorithms proposed in the literature [5,10], not all are suitable for fingerprint images. A fingerprint image of low quality due to factors such as different properties of sensors, temporary or permanent cuts and bruises in the skin creates a l