The performance of an automatic fingerprint recognition system relies heavily on the quality of input fingerprint images. This paper presents a novel approach to assess the local and global quality of fingerprint image by estimating the ridge continuity measure, which reflects the intrinsic characteristics of quality. The ridge continuity measure is computed by combining orientation coherence and the first and second order directional derivatives of the image. The calculation of minutiae reliability is also derived from the local quality map. Qualitative and quantitative experiments are carried out to evaluate the proposed quality measure. The experimental results show that it is effective for estimating the image quality, and can be used for quality control in enrollment stage and improving the recognition rate in matching stage.