| There are many human biometric features that can be used to confirm the identity, such as voice, hand geometry, face, fingerprint and retinal pattern of eyes. Fingerprint images vary in quality. In order to ensure that the performance of the Automatic fingerprint Identification system (AFIS) will be robust with the respect to the quality of the input images, it is essential to incorporate a fingerprint enhancement module in the AFIS system. Fingerprint is unique identifiers of individuals and has been used for a long time. Government agencies (such as the police) and many kinds of departments needing high security have to collect increasing amount of fingerprints for transmission, storage, and automated analysis.The collection ,formation and transportation of the fingerprint image in the AFIS is often disturbed by the noise and quality difference of the collection equipments. To reduce the influence of noise , it is essential to implement measures to optimize the fingerprint under the course of preprocessing.Automatic and reliable extraction minutiae algorithms relies heavily on the quality of the digital images, so the stage of preprocessing is of vital importance . Due to a number of factors ( aberrant formations of epidermal ridges of fingerprints, postnatal marks, occupational marks, problems with acquisition devices ,etc),digital fingerprint images may not be always have well-defined ridge/valley tructures ,which the minutiae extraction algorithms usually assume.I referred some classic algorithms on fingerprint enhancement , such as the fingerprint enhancement by the unsharp masking. This dissertation presents the effective mechanisms for fingerprint images edge enhancement; and it compares Daubechies and Haar wavelet decompositon and reconstruction algorithms and apply non-linear function after decompositon .The combined approach to makes it possible to resolve fine structures in clear areas while reducing the risk of enhancing noise in blurred or fragmented areas. |
PDF Full Text Request