We describe two image matching techniques that owe their success to a combination of geometric and photometric constraints. In the first, images are matched under similarity transformations by using local intensity invariants and semi-local geometric constraints. In the second, 3D curves and lines are matched between images using epipolar geometry and local photometric constraints. Both techniques are illustrated on real images. We show that these two techniques may be combined and are complementary for the application of image retrieval from an image database. Given a query image, local intensity invariants are used to obtain a set of potential candidate matches from the database. This is very efficient as it is implemented as an indexing algorithm. Curve matching is then used to obtain a more significant ranking score. It is shown that for correctly retrieved images many curves are matched, whilst incorrect candidates obtain very low ranking.