Image orientation detection with integrated human perception cues (or which way is up)

In this paper, we propose a set of human perceptual cues used jointly to automatically detect image orientation. The cues used are: orientation of faces, position of the sky, brighter regions, and textured objects, and symmetry. We combine these cues in a Bayesian framework, and the photo acquiring model has been considered carefully as the prior knowledge of the image orientation. Results on more than a thousand different images provide a compelling argument that our approach is a viable one.