The performance of an automatic fingerprint authentication system relies heavily on the quality of fingerprint images. Besides, the effective evaluation and quality classification of fingerprint images is of paramount significance in the applicability research of fingerprint recognition algorithm. In this paper, an effective quality classification method for fingerprint image based on neural network is proposed. The quality indexes comprise effective area, energy concentration, spatial consistency and directional contrast, and neural network is applied to achieve quality classification of fingerprint images. The experimental results show the method proposed could improve fingerprint image quality classification accuracy more effectively than individual quality index threshold segmentation and linear weighted sum method.