Robust Fingerprint Image Enhancement: An Improvement to Directional Analysis of Fingerprint Image using Directional Gaussian Filtering and Non-Subsampled Contourlet Transform Muhammad Talal Ibrahim 1 , Tariq Bashir 2 and Ling Guan 3 1,3 Ryerson Multimedia Research Lab Ryerson University, Toronto, Canada. 2 Dept. of Electrical Engineering COMSATS Institute of Information Technology, Islamabad, Pakistan. 1 muhammadtalal.ibrahi@ryerson.ca, 2 tariq bashir@comsats.edu.pk, 3 lguan@ee.ryerson.ca Abstract In this paper, a new ﬁngerprint image enhancement method based on the integration of Directional Gaussian ﬁltering and Non-Subsampled Contourlet Transform (NSCT) has been proposed. As the ﬁngerprint images suffers from non-uniform illumination, so there is a need to completely remove or reduce the non-uniform illumination present in the ﬁngerprint image before applying any enhancement technique. In this paper, we have used bandpass ﬁlter for the elimination of non-uniform illumination and for the creation of frequency ridge image. Further the directional noise present in the ﬁngerprint image have been removed by using the Directional Gaussian ﬁlter and the noise-free image was decomposed into Non-Subsampled directional images by using NSCT. Lately, we construct an enhanced image through a block-by-block process which compares the energy of all the directional images and picks the one that provides maximum energy. Further, binarization and thinning are also applied on the enhanced image. 1 Introduction Minutiae extraction is one of the most important steps for automatic ﬁngerprint identiﬁcation and classiﬁcation systems (AFIS). The performance of any ﬁngerprint veriﬁcation system highly depends on the quality of ﬁngerprint image. So, we can- not deny the importance of ﬁngerprint enhancement module in the automatic ﬁngerprint identiﬁcation and classiﬁcation sys- tems. Several techniques have been proposed in the literature for ﬁngerprint image enhancement but the the need of improve- ment is still there. From the last decade, directional analysis of ﬁngerprint for the enhancement, feature extraction and matching have been widely used. One of the most famous and widely used directional ﬁlter is Gabor Filter [1, 2, 3, 4]. They have both frequency-selective and orientation-selective properties and have optimal joint resolution in both spatial and frequency domains. They have been used in [5], where the gradient di- rection of the pixels have been identiﬁed and then the image is being ﬁltered according to the gradient direction and com- bined to get an enhanced image. In [6], the limitations of tra- ditional Gabor ﬁlter were overcomed and the Log-Gabor ﬁlter Figure 1. Proposed Fingerprint Image Enhancement System Figure 2. Fingerprint Test Image was introduced for the enhancement purpose. The use of the Directional Gaussian ﬁltering has been proposed in [7], where the Gabor Wavelets were applied to the noise-free image after passing the input image though Directional Gaussian ﬁltering. In this paper directional Gaussian ﬁltering has been used for the smoothing purpose whereas directional analysis is per- formed by the Non-Subsampled Contourlet Transform on the smoothed image and then directional energies are used for the reconstruction of enhanced image. Finally the enhanced im- age is binarized and thinned. Rest of the paper is organized in the following manner: Section II covers our proposed system and discussion while in Section III, some of the experimental results and comparisons are provided. 2 Fingerprint Image Enhancement The proposed system takes the ﬁngerprint as an input for the enhancement as shown in Fig. 1. The main steps involved in the proposed system are described below in a sequential order. Tenth IEEE International Symposium on Multimedia 978-0-7695-3454-1/08 $25.00 © 2008 IEEE DOI 10.1109/ISM.2008.108 280