A computational vision approach is presented for the estimation of 2-D translation, rotation, and scale from two partially overlapping images. An illuminant direction estimation method is first used to obtain an initial estimate of camera rotation. A small number of feature points are then located based on a Gabor wavelet model for detecting local curvature discontinuities. An initial estimate of scale and translation is obtained by pairwise matching of the feature points detected from both frames. Finally, hierarchical feature matching is performed to obtain an accurate estimate of translation, rotation and scale. The approach results in a fast method that produces excellent results even when large rotation has occurred between the two frames and the images are devoid of significant features. Experiments with synthetic and real images show that this algorithm yields accurate results when the scale between the image pair differ by up to 10%, the overlap between the two frames is as small as 35%, and the camera rotation between the two frames is significant.