Automatic fingerprint identification is one of the most significant biometrics technology. Preprocessing of fingerprint image play an important role in automatic fingerprint identification system(AFIS) and segmenting the ridges and valleys from fingerprint images is the basic task of preprocessing. This paper presents a new segment method for the ridges and valleys of fingerprint images. The ridges and valleys are considered as roof edge and their two sides are taken for step edges

then ridges and valleys can be located based on roof edge detection of multi scales B spline wavelet

and the area of the ridges and valleys is decided by the step edges. The valid scale range for roof target detection is discussed in detail

and we also give the simply and concretely segment method. The effectiveness of this algorithm has been testified for different quality fingerprints images. It must be point out that this segment method can be applied to detection of other similar roof targets.