An algorithm for reducing the effect of compression/decompression techniques on fmgerprint minutiae

We show in this paper that the wavelet transform is an effective technique for significantly compressing fingerprint images, while retaining the necessary structural details for accurate identification. The paper presents a new algorithm for extracting the fundamental identification features for use in automated fingerprint matching systems. Contrary to existing algorithms, the method presented here is tested on compressed/decompressed fingerprint images. We show that using the compression algorithm proposed earlier by the author, we are able to obtain a valid description of the fingerprints at compression ratios down to 50:1.