-------------------------------------------------- Dr. JuCheng Yang, Division of Electronics & Information Engineering, Chonbuk National University, 664-14 1Ga Deonjin-dong Deonjin-gu, Jeonju, Jeonbuk, 561-756, Korea. Email: biometricscode@gmail.com http://yangjucheng.chonbuk.ac.kr/ ----------------------------------------------------- Abstract A novel texture-based Automatic Fingerprint Authentication System (AFAS) is proposed. A fingerprint image is preprocessed to enhance the image by Short Time Fourier Transform (STFT) analysis. Then, three sets of invariant moment features, as a kind of texture features, are extracted from three different sizes of Region of Interest (ROI) areas based on the reference point from the enhanced fingerprint image. Each set of invariant moments contain seven invariant moments. Fingerprint verification is realized by Euclidean distance between the two corresponding features of the test fingerprint image and template fingerprint image in the database. Reference [1] Sharat C., Alexander N. C. Venu G., Fingerprint enhancement using STFT analysis, Pattern Recognition, In Press, Corrected Proof, Available online 22 August 2006. [2] Kenneth N. and Josef B., Localization of corresponding points in fingerprints by complex filtering, Pattern Recognition Letters, 24, pp2135-2144, 2003. [3] Ju Cheng Yang, Sook Yoon, Dong Sun Park, ¡°Applying Learning Vector Quantization Neural Network for Fingerprint Matching¡±, Lecture Notes in Artificial Intelligence (LNAI 4304), Springer, Berlin, Dec., 2006. (SCI ) [4]Ju Cheng Yang, Dong Sun Park, ¡°A Fingerprint Verification Algorithm Using Tessellated Invariant Moment Features¡±, Neurocomputing, Vol. 71(10-12) pp. 1939-1946, 2008.(SCI ) Acknowledgement The author would like to thank some code suppliers such as Chikkerur Sharat and Luigi ROSA for their contributions. Using Guide: matlab 6.5 version (or over version)+ image proceesing tools; The 1st step, change the files directory as the matlab current directory; The 2nd step, in the "command" window, input "test", then "Enter"; The 3rd step, GUI will be shown. "readme.txt" file: this is the introduce file for the algorithm; if you want more information, see the website http://yangjucheng.chonbuk.ac.kr/