In this paper, we present a new feature extraction method for face recognition. The digital curvelet transform is used to extract the face features. In our method, an original image is convolved with 6 Gabor filters corresponding to various orientations and scales to give its Gabor representation, then the ridgelet transform is applied to each Gabor face set. Our experiments were carried on the ORL database. Dealing with the face image size of 46times56, our method acquires a Gabor face set of 138times112. Then, the Gabor representation is analyzed by the ridgelet transform followed by the 2DPCA which computes the eigenvectors of the ridgelet image covariance matrix. Experiments showed that the correct recognition rate of our method is up to 95.5%.