In a fingerprint recognition system only fingerprint region of scanned image should be taken into
account. Hence, it is necessary the ROI (Region of Interest) to be segmented from the background.
Different methods have been proposed for fingerprint segmentation. In this paper, some of the most
important methods are introduced and implemented. Then one of them is modified and based on it, an
adaptive and supervised method is proposed. Finally, all of implemented methods and the proposed method
are evaluated and compared to each other. The DB2_B of FVC2004 is selected as a standard database, to
implement each method. The experimental results demonstrate the effectiveness of the proposed method,
concerning the extraction of ROI, especially in low quality images