A Survey on Approaches to Improve Quality of Fingerprint Image and Template Security

A biometric is a distinct biological trait that can be used to recognize a person. Fingerprints have been used for over a century and are the most widely used for user identification. Fingerprint identification is commonly employed in Forensic science to support criminal investigations and in biometric systems such as civilian and commercial identification devices.Fingerprint is the pattern of ridges and valley on the inner surface of a finger or a thumb. The low quality fingerprint imagesused for feature extraction and matching will not produce efficient results. To deal with this various methods for enhancing low-quality fingerprints images are discussed. In addition to enhancement, the storage of fingerprint template is also an important issue. Because when the hacker steels the template from the database, it can be misused. To avoid this problem, various template security techniques are surveyed.In this paper various image quality enhancement techniques and template security techniques are reviewed in the literature. INTRODUCTION Biometric systems automatically determine or verify a person’s identity based on his anatomical and behavioral characteristics such as fingerprint, palmprint, vein pattern, finger knuckles, face, Iris, voice and gait. Biometric trait, called the feature set is unique for each and every person. The feature set obtained during enrolment is stored in the system database as a template. One of the momentous issues in biometric systems is protecting the template of a user which is usually stored in a database or a smart card. Stolen biometric templates can be used to compromise the security of the system in the following two ways: (i) The stolen template can be replayed to the matcher to gain unauthorized access, and (ii) A physical spoof can be created from the template to gain unauthorized access to the system. An attacker can furtively acquire the biometric information of a genuine user. Hence, spoof attacks are possible even when the attacker does not have access to the biometric template. However, the attacker needs to be in the physical nearness of the person he is attempting to impersonate in order to stealthily acquire his biometric trait. On the other hand, even a remote attacker can create a physical spoof if he gets access to the biometric template information. Unlike passwords, when biometric templates are compromised, it is not possible for a genuine user to revoke his biometric identifiers and switch to another set of uncompromised identifiers. Due to this irretrievable nature of biometric data, an attack against the stored templates constitutes a major security and privacy peril in a biometric system. Since a biometric trait is an everlasting link between a person and his identity, it can be easily prone to abuse in such a way that a person’s right to privacy and secrecy is compromised. Hence, strategies to protect biometric template and to ensure an individual’s privacy are urgently needed. Human experts routinely use the context information of fingerprint images, such as ridge continuity and regularity to help in identifying them. This means that the underlying morphogenetic process that produced the ridges does not allow for irregular breaks in the ridges except at ridge endings. Because of the regularity and continuity properties of the fingerprint image, occluded and corrupted regions can be recovered using the contextual information from the surrounding area. Such regions are regarded as “recoverable” regions. The efficiency of an automated enhancement algorithm depends on the extent to which they utilize the contextual information. The following literature describes several enhancement methods for fingerprint images. LITERATURE SURVEY FINGERPRINT ENHANCEMENT Novel Adaptive Approach Tahmasebi and Kasaei [1] presented a novel Adaptive Approach for fingerprint enhancement filter design. To improve the efficiency of the enhancement process, the designed filter adapts itself to the characteristics of input images. Moreover, the filter parameters are automatically calculated with no need of any predetermined parameters. Different filter masks are adapted for different image scales to improve the efficiency of the enhancement process. The algorithm is fast and the required computational load is negligible. Chain code image representation Zhixin Shi and VenuGovindaraju[2] presented a novel use of chain code image representation in fingerprint image enhancement and minutiae extraction. The chaincode representation allows efficient image quality enhancement and detection of fine minutiae feature points. For image enchantment binarization algorithm is used binarized after a quick averaging to generate its chaincode representation. The direction field is estimated from a set of selected chaincodes. The original gray-scale image is then enhanced by a filtering algorithm. The minutiae are detected using a sophisticated ridge contour following procedure. Short Time Fourier Transform (STFT) Analysis Sharat et.al [3] presented new approach for fingerprint enhancement based on Short Time Fourier Transform(STFT) Analysis.The algorithm simultaneously estimates all the intrinsic properties of the fingerprints such Janani B et al | International Journal of Computer Science Engineering and Technology( IJCSET) | November 2014 | Vol 4, Issue 11,333-335