An improved technique for evolving wavelet coefficients for fingerprint image compression

Abstract

In this paper, an improved technique for evolving wavelet coefficients refined for compression and reconstruction of fingerprint images is presented. The FBI fingerprint compression standard [1, 2] uses the cdf 9/7 wavelet filter coefficients. Lifting scheme is an efficient way to represent classical wavelets with fewer filter coefficients [3, 4]. Here Genetic algorithm (GA) is used to evolve better lifting filter coefficients for cdf 9/7 wavelet to compress and reconstruct fingerprint images with better quality. Since the lifting filter coefficients are few in numbers compared to the corresponding classical wavelet filter coefficients, they are evolved at a faster rate using GA. A better reconstructed image quality in terms of Peak-Signal-to-Noise-Ratio (PSNR) is achieved with the best lifting filter coefficients evolved for a compression ratio 16:1. These evolved coefficients perform well for other compression ratios also.

Evolution of Better Wavelet Coefficients for Fingerprint Image Compression Using Cropped Images

“…In this work, symmetrical lifting coefficients of cdf9/7 wavelet have been evolved using GA [4,12]. The classical cdf 9/7 wavelet system consists of 16 coefficients, whereas the symmetrical lifting system consist only 4 coefficients.…”

“…In the earlier works [11,12,17] the training image set contained four numbers of full-size (300x300 pixels) fingerprint images. In the present work, to speed up the evolution process, training image set was formed by images cropped to smaller sizes.…”

“…In order to have a fair comparison with the previous results and a speedy evolution of the lifting coefficients, the symmetric lifting scheme [4,12] with only 4 coefficients has been used in this work. Better lifting coefficients have been evolved in a shorter time with training sets comprised of cropped fingerprint images.…”

“…Altogether there are 16 coefficients [11]. Peak-Signal-to-Noise-Ratio (PSNR) and Root Mean Squared Error (RMSE) are the two measures of image compression performance [12]. The lifting scheme introduced by W. Sweldens [7,13,14] is an effective technique to represent classical wavelets with lesser number of coefficients.…”

“…An average PSNR improvement of 0.75dB was reported. Shanavaz and Mythili [12] proposed a method by which cdf9/7 lifting coefficients were evolved using GA. The population size was 250 and number of generations was 1000.…”