Rotated Wavelet Filters-Based Fingerprint Recognition

Abstract

A novel approach for feature extraction of¯ngerprint matching is proposed by using twodimensional (2D) rotated wavelet¯lters (RWF). 2D RWF are used to capture the characterization of diagonally oriented information present in¯ngerprint image. Proposed method extracts the signi¯cant information from small area of¯ngerprint image. Experimental results conducted on standard database of Bologna University and FVC2002 indicate that the proposed method improves the genuine acceptance rate (GAR) from 92.14% to 96.12% and reduces false acceptance rate (FAR) from 25.2% to 21.2% on Bologna University database and it reduces FAR from 36.71% to 22.79% on FVC2002 database compared with discrete wavelet transform-based approach.

Finger Vein Recognition using Rotated Wavelet Filters

“…Discrete Wavelet Transform (DWT) is a popular mathematical tool used for transforming and analyzing the signal in the time and frequency domain [13,18]. The standard DWT decomposes an image f(x, y) in terms of the shifted and dilated wavelet functions at {Ψ0 0 , Ψ90 0 , Ψ±45 0 } and the scaling function ϕ (x, y) are represented by equation (1) and (2) respectively [13].…”

“…The standard DWT decomposes an image f(x, y) in terms of the shifted and dilated wavelet functions at {Ψ0 0 , Ψ90 0 , Ψ±45 0 } and the scaling function ϕ (x, y) are represented by equation (1) and (2) respectively [13].…”

“…an average image. The LH subband (Low frequency components row and High frequency component column wise), the HL subband (High frequency components row and Low frequency component column wise), and the HH subband (High frequency components row and column wise) gives horizontal, vertical and diagonal information of an input image respectively [13,15].…”

“…The high pass and low pass 1D Daubechies eight tap wavelet filter coefficients are extracted by using the wfilters ( ) function in MATLAB. The 2D wavelet filters [12,13] are created using 1D wavelet filter coefficients using equation (3).…”

Age Group Recognition using Human Facial Images

“…The researchers explored many classification methods for classifying extracted features into age groups, such as k-nearest neighbors (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN), Euclidian Distance Classifier etc. [10,14,[16][17][18][19]. Age group recognition system can be used for many applications such as System access control where young kids can be denied to access adult websites, sell of cigarettes and alcohol from vending machine to underage people can be declined, age of people who spend more time to see particular advertisement can be find out by Ad-agency, the videos and photographs of users can be reclaimed by specifying particular age group [9], [11].…”