| 摘要 |
The method involves selecting a reference image from a set of images, and detecting an orientation of an image based on the orientation of the reference image. Sub-pictures of the image and the reference image are determined. The sub-pictures have the same size with respect to the image in which are positioned the sub-pictures. A visual distance between the image and the reference image is calculated. An independent claim is also included for a device of detecting orientation of an image in a set of images. |
