Changing in real-time the perspective of objects captured in images

摘要

Capturing an image of an object from a captured perspective and creating a plurality of candidate object areas. Each candidate object area potentially enclosing the object captured in the image. From the plurality of candidate object areas, a candidate object area is selected as enclosing the object. A corrected image of the object is generated based on the selected candidate object area. The corrected image shows the object transformed to a corrected perspective. The corrected image is displayed.