A new median filter based fingerprint recognition algorithm

Abstract In this paper, a new algorithm for fingerprint recognition is presented. It is called the Histogram-Partitioning, Median-Filtering Fingerprint Recognition Algorithm (HMFA). The performance of the algorithm is tested through ensemble averaging of the mean square error. It is applied on different fingerprints having various backgrounds, resolutions and dimensions. Initially, a database is formed using several fingerprints. Those are subjected to various types of noise, such as impulsive and Gaussian noises. Then HMFA is applied to filter the noise. Next, using the query designed for the algorithm, the fingerprint recognition from the database is done. This is accomplished by selecting the fingerprint from the database that produces the least mean square error in comparison to the fingerprint in question. The assessment is made using ensemble averaging.

[1]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[2]  Thomas S. Huang,et al.  The Effect of Median Filtering on Edge Estimation and Detection , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  G. Aguilar,et al.  Fingerprint Recognition , 2007, Second International Conference on Internet Monitoring and Protection (ICIMP 2007).

[4]  A. Procházka,et al.  NON-LINEAR MEDIAN FILTERING OF BIOMEDICAL IMAGES , 2022 .

[5]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[6]  Antonio. Garcia-Valdecasas,et al.  Two-Dimensional Imaging , 1996 .

[7]  Mayer Aladjem,et al.  Fingerprint image enhancement using filtering techniques , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  R. Ostrovsky,et al.  Fingerprint Recognition , 2008 .

[9]  Antonios Gasteratos,et al.  A new content based median filter , 2004, 2004 12th European Signal Processing Conference.