关键词: Harris角点检测器, 指纹图像分割, 形态学

Abstract: Fingerprint segmentation is one of critical pre-processing steps in automatic fingerprint identification system.This paper proposes an adaptive fingerprint segmentation based on Harris corner detector.At first，Harris operator is used to compute the strength of Harris corners in the fingerprint image，and then a threshold-setting method is adopted to compute adaptively the threshold for the early segmentation.Morphology is applied as post-processing to reduce the number of classification errors，the area parameter is used to remove remaining noised region to get the final segmented image.The experimental results on databases of FVC2004 prove that the proposed algorithm provides very accurate segmentation of valid ridge region.Moreover，this classification method also has a great robustness to those fingerprint images with low quality.

Key words: Harris corner detector, fingerprint segmentation, morphology