Evolved Wavelets for Improved Fingerprint Compression

In this paper an attempt has been made to develop new wavelet transform that consistently outperform the 9/7and 5/3 Discrete Wavelet Transform (DWT) for fingerprint image compression and reconstruction performances. Experimental results were obtained using 9/7 and 5/3 wavelet transforms for different types of fingerprint images. These results shows that the proposed method is consistently outperforms on finger print images for lossless image compression, in terms of Compression Ratio (CR), Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Encoding time, decoding time and transforming time or decomposition time.

Provided by: International Journal on Computer Science and Technology (IJCST) Topic: Security Date Added: Sep 2011 Format: PDF

Find By Topic