论文部分内容阅读
Abstract: Fingerprint is one of the most universally accepted biometrics used in different and relevant fields of man’s endeavours including business transactions and human security. They have been used for the implementation of series of Automatic Fingerprint Identification Systems (AFIS) that have proved very adequate and efficient. Building an AFIS requires the implementation of different algorithms. One of such algorithms is the one concerned with fingerprint image enhancement which involves segmentation, normalization, ridge orientation estimation, ridge frequency estimation, filtering, binarization and thinning. In this research, the implementation of a modified approach to an existing ridge orientation estimation algorithm is presented with a view to increase speed and accuracy. The implementation was carried out in an environment characterized by Window Vista Home Basic operating system as platform and Matrix Laboratory (MatLab) as frontend engine. Synthetic images as well as real fingerprints obtained from selected staff and students of The Federal University of Technology, Akure (FUTA), Nigeria and the standard FVC2000 fingerprint database DB2 were used to test the adequacy of the resulting algorithm. The results show that the modified algorithm estimated the orientation with significant improvement over the original version.
Key words: Fingerprint, AFIS (automatic fingerprint identification systems), ridge orientation, biometrics, singular point.
1. Introduction
Fingerprint has continued to enjoy international recognition and approval in human verification and identification. It has continued to show superiority over other biometrics like face, iris, voice, gait, palm, hand, signature, middle ware and so on [1]. Fingerprints exist in different patterns ranging from left loop, right loop, whorl, arch and tented arch as shown in Fig. 1 [2]. In the loop pattern, the ridges enter from either side, re-curve round the core point (which is the point of maximum orientation) and pass out or tend to pass out the same side they entered. In the right loop pattern, the ridges enter from the right side while they enter from the left side in the left loop. In a whorl pattern, the ridges are usually circular round the core point while in the arch pattern, the ridges enter from one side, make a rise round the core point and exit generally on the opposite side.
The main components of any fingerprint used for identification and security control are the features it possesses. The features exhibit uniqueness defined by type, position and orientation from fingerprint to fingerprint and they are classified into global and local features [3-6].
Global features are those characteristics of the fingerprint that could be seen with the naked eye. They are the features that are characterized by the attributes that capture the global spatial relationships of a fingerprint. Global features include ridge pattern, type, orientation, spatial frequency, curvature, position and count. Others are type lines, core and delta areas. The local features are also known as minutiae points. They are the tiny, unique characteristics of fingerprint ridges that are used for positive identifications. Local features contain the information that is in a local area only and invariant with respect to global transformation.
Reliable and sound verification of fingerprints in any AFIS is always preceded with a proper detection and extraction of its features. A fingerprint image is firstly enhanced before the features contained in it could be detected or extracted. A well enhanced image will provide a clear separation between the valid and spurious features. Spurious features are those minutiae points that are created due to noise or artifacts and they are not actually part of the fingerprint [6-8]. This paper presents a practical discussion on the fingerprint ridge orientation estimation which is a very important part of the enhancement process. Section 2 presents a clear discussion on the modified fingerprint ridge orientation estimation algorithm while section 3 focuses on findings from conducted experiments. The conclusions are presented in section 4.
2. Fingerprint Ridge Orientation Estimation
In every fingerprint image, the ridges form patterns that flow in different directions. The orientations of ridges at locations A(x, y), and B(x, y) shown in Fig. 2 are the directions of the flow over a range of pixels.
The sequence of activities involved in fingerprint ridge orientation estimation is presented in Fig. 3.
There are two regions that describe any fingerprint image: namely the foreground region and the background region. The foreground regions contain the ridges and valleys. The ridges are the raised and dark regions of a fingerprint image while the valleys are the low and white regions between the ridges. The foreground regions often referred to as the Region of Interest (RoI) is shown for the image presented in Fig. 4. The background regions are mostly the outside regions where the noises introduced into the image during enrolment are mostly found. The essence of segmentation is to reduce the burden associated with image enhancement by ensuring that focus is only on the foreground regions.
Normalization on its own is performed on the segmented fingerprint ridge structure for the standardization of the level of variations in the image grey-level values. By normalization, the grey-level values are made to fall within certain range good enough for improved image contrast and brightness. The modified fingerprint ridge segmentation and normalization algorithms implemented in Ref. [8] were adopted for this research. The algorithms sufficiently and effectively separate the foregrounds from the backgrounds using variance threshold approach. The segmented images were normalized to improve on their ridges and contrasts.
References
[1] C. Roberts, Biometrics, available online at: http://www.ccip.govt.nz/newsroom/informoation-notes/2 005/biometrics.pdf, accessed: July 2009.
[2] T.-Y. Jea, V. Govindaraju, A minutia-based partial fingerprint recognition system, Pattern Recognition 38(2005) 1672-1684.
[3] C. Michael, E. Imwinkelried, Defence practice tips, a cautionary note about fingerprint analysis and reliance on digital technology, Public Defense Backup Centre Report, 2006.
[4] O.C. Akinyokun, C.O. Angaye, G.B. Iwasokun, A framework for fingerprint forensic, in: Proceeding of the First International Conference on Software Engineering and Intelligent System, Covenant University, Ota, Nigeria, 2010, pp. 183-200.
[5] O.C. Akinyokun, E.O. Adegbeyeni, Scientific evaluation of the process of scanning and forensic analysis of fingerprints on ballot papers, in: Proceedings of Academy of Legal, Ethical and Regulatory Issues, Vol. 13, No. 1, New Orleans, 2009.
[6] G.B. Iwasokun, O.C. Akinyokun, B.K. Alese, O. Olabode, Adaptive and faster approach to fingerprint minutiae extraction and validation, International Journal of Computer Science and Security 5 (4) (2011) 414-424.
[7] C. Sharat, C. Wu, V. Govindaraju, A systematic approach for feature extraction in fingerprint pattern recognition, Center for Unified Biometrics and Sensors (CUBS), University at Buffalo, NY, USA, 2004.
[8] G.B. Iwasokun, O.C. Akinyokun, B.K. Alese, O. Olabode, Fingerprint image enhancement: Segmentation to thinning, International Journal of Advanced Computer Science and Applications Indian 3 (1) (2012).
[9] L. Hong, Y. Wan, A. Jain, Fingerprint image enhancement: Algorithm and performance evaluation, Pattern Recognition and Image Processing Laboratory, Department of Computer Science, Michigan State University, 2006, pp. 1-30.
[10] R. Thai, Fingerprint image enhancement and minutiae extraction, Ph.D. Thesis, School of Computer Science and Software Engineering, University of Western Australia, 2003.
[11] P. Kovesi, MATLAB functions for computer vision and image analysis, School of Computer Science and Software Engineering, University of Western Australia, available online at: http:/www.cs.uwa.edu.au/~pk/Research/Matlab Fns/Index.html, accessed: February 20, 2010.
Key words: Fingerprint, AFIS (automatic fingerprint identification systems), ridge orientation, biometrics, singular point.
1. Introduction
Fingerprint has continued to enjoy international recognition and approval in human verification and identification. It has continued to show superiority over other biometrics like face, iris, voice, gait, palm, hand, signature, middle ware and so on [1]. Fingerprints exist in different patterns ranging from left loop, right loop, whorl, arch and tented arch as shown in Fig. 1 [2]. In the loop pattern, the ridges enter from either side, re-curve round the core point (which is the point of maximum orientation) and pass out or tend to pass out the same side they entered. In the right loop pattern, the ridges enter from the right side while they enter from the left side in the left loop. In a whorl pattern, the ridges are usually circular round the core point while in the arch pattern, the ridges enter from one side, make a rise round the core point and exit generally on the opposite side.
The main components of any fingerprint used for identification and security control are the features it possesses. The features exhibit uniqueness defined by type, position and orientation from fingerprint to fingerprint and they are classified into global and local features [3-6].
Global features are those characteristics of the fingerprint that could be seen with the naked eye. They are the features that are characterized by the attributes that capture the global spatial relationships of a fingerprint. Global features include ridge pattern, type, orientation, spatial frequency, curvature, position and count. Others are type lines, core and delta areas. The local features are also known as minutiae points. They are the tiny, unique characteristics of fingerprint ridges that are used for positive identifications. Local features contain the information that is in a local area only and invariant with respect to global transformation.
Reliable and sound verification of fingerprints in any AFIS is always preceded with a proper detection and extraction of its features. A fingerprint image is firstly enhanced before the features contained in it could be detected or extracted. A well enhanced image will provide a clear separation between the valid and spurious features. Spurious features are those minutiae points that are created due to noise or artifacts and they are not actually part of the fingerprint [6-8]. This paper presents a practical discussion on the fingerprint ridge orientation estimation which is a very important part of the enhancement process. Section 2 presents a clear discussion on the modified fingerprint ridge orientation estimation algorithm while section 3 focuses on findings from conducted experiments. The conclusions are presented in section 4.
2. Fingerprint Ridge Orientation Estimation
In every fingerprint image, the ridges form patterns that flow in different directions. The orientations of ridges at locations A(x, y), and B(x, y) shown in Fig. 2 are the directions of the flow over a range of pixels.
The sequence of activities involved in fingerprint ridge orientation estimation is presented in Fig. 3.
There are two regions that describe any fingerprint image: namely the foreground region and the background region. The foreground regions contain the ridges and valleys. The ridges are the raised and dark regions of a fingerprint image while the valleys are the low and white regions between the ridges. The foreground regions often referred to as the Region of Interest (RoI) is shown for the image presented in Fig. 4. The background regions are mostly the outside regions where the noises introduced into the image during enrolment are mostly found. The essence of segmentation is to reduce the burden associated with image enhancement by ensuring that focus is only on the foreground regions.
Normalization on its own is performed on the segmented fingerprint ridge structure for the standardization of the level of variations in the image grey-level values. By normalization, the grey-level values are made to fall within certain range good enough for improved image contrast and brightness. The modified fingerprint ridge segmentation and normalization algorithms implemented in Ref. [8] were adopted for this research. The algorithms sufficiently and effectively separate the foregrounds from the backgrounds using variance threshold approach. The segmented images were normalized to improve on their ridges and contrasts.
References
[1] C. Roberts, Biometrics, available online at: http://www.ccip.govt.nz/newsroom/informoation-notes/2 005/biometrics.pdf, accessed: July 2009.
[2] T.-Y. Jea, V. Govindaraju, A minutia-based partial fingerprint recognition system, Pattern Recognition 38(2005) 1672-1684.
[3] C. Michael, E. Imwinkelried, Defence practice tips, a cautionary note about fingerprint analysis and reliance on digital technology, Public Defense Backup Centre Report, 2006.
[4] O.C. Akinyokun, C.O. Angaye, G.B. Iwasokun, A framework for fingerprint forensic, in: Proceeding of the First International Conference on Software Engineering and Intelligent System, Covenant University, Ota, Nigeria, 2010, pp. 183-200.
[5] O.C. Akinyokun, E.O. Adegbeyeni, Scientific evaluation of the process of scanning and forensic analysis of fingerprints on ballot papers, in: Proceedings of Academy of Legal, Ethical and Regulatory Issues, Vol. 13, No. 1, New Orleans, 2009.
[6] G.B. Iwasokun, O.C. Akinyokun, B.K. Alese, O. Olabode, Adaptive and faster approach to fingerprint minutiae extraction and validation, International Journal of Computer Science and Security 5 (4) (2011) 414-424.
[7] C. Sharat, C. Wu, V. Govindaraju, A systematic approach for feature extraction in fingerprint pattern recognition, Center for Unified Biometrics and Sensors (CUBS), University at Buffalo, NY, USA, 2004.
[8] G.B. Iwasokun, O.C. Akinyokun, B.K. Alese, O. Olabode, Fingerprint image enhancement: Segmentation to thinning, International Journal of Advanced Computer Science and Applications Indian 3 (1) (2012).
[9] L. Hong, Y. Wan, A. Jain, Fingerprint image enhancement: Algorithm and performance evaluation, Pattern Recognition and Image Processing Laboratory, Department of Computer Science, Michigan State University, 2006, pp. 1-30.
[10] R. Thai, Fingerprint image enhancement and minutiae extraction, Ph.D. Thesis, School of Computer Science and Software Engineering, University of Western Australia, 2003.
[11] P. Kovesi, MATLAB functions for computer vision and image analysis, School of Computer Science and Software Engineering, University of Western Australia, available online at: http:/www.cs.uwa.edu.au/~pk/Research/Matlab Fns/Index.html, accessed: February 20, 2010.