Efficient Filtering of Noisy Fingerprint Images

Abstract

Fingerprint identification is an important field in the wide domain of biometrics with many  applications, in different areas such: judicial, mobile phones, access systems, airports. There are  many elaborated algorithms for fingerprint identification, but none of them can guarantee that the  results of identification are always 100 % accurate. A first step in a fingerprint image analysing  process consists in the pre-processing or filtering. If the result after this step is not by a good quality  the upcoming identification process can fail. A major difficulty can appear in case of fingerprint  identification if the images that should be identified from a fingerprint image database are noisy  with different type of noise. The objectives of the paper are: the successful completion of the noisy  digital image filtering, a novel more robust algorithm of identifying the best filtering algorithm and  the classification and ranking of the images. The choice about the best filtered images of a set of 9  algorithms is made with a dual method of fuzzy and aggregation model. We are proposing through  this paper a set of 9 filters with different novelty designed for processing the digital images using  the following methods: quartiles, medians, average, thresholds and histogram equalization, applied  all over the image or locally on small areas. Finally the statistics reveal the classification and  ranking of the best algorithms.