Using vanishing points to correct camera rotation in images

Abstract

Vanishing points provide valuable information regarding the camera model used to capture an image. To explore the relationship between classes of camera models and the location of vanishing points, typical consumer photographic behavior is considered. Based on these findings, an algorithm is presented that can automatically remove the tilted appearance of an image captured with a camera rotated about the principal axis. The algorithm includes detecting vanishing points in an image, determining if any vanishing points are associated with vertical lines in the scene, computing the angle of rotation, and rotating the image. Results of the algorithm are shown for a set of images. The algorithm performs well and produces pleasing images from original images that contain undesirable levels of tilt.