An effective algorithm for fingerprint reference point detection based on filed flow curves

In this paper a novel approach is proposed to detect reference point for fingerprint images. Reference point extraction is a key component in automatic fingerprint identification and recognition systems. A new method was proposed for fingerprint reference point extraction, based on field flow curve and clustering. High curvature points in the flow curves are used in our reference point detection. Because we use flow curve instead of ridge for reference point detection, our method is robust to noise and has a good result on fingerprint image with low quality. Also our method has the ability to detect a reference point for an arch class fingerprint which is hard for other methods to detect it. The experiments are conducted on FVC2002-DB2a and FVC2004 to measure the performance of our reference point detection. Experimental results show that our algorithm is robust and it has better results than other approaches.