公开(公告)号：US09521270B1

公开(公告)日：2016-12-13

申请号：US14142673

申请日：2013-12-27

Applicant: Google Inc.

Inventor： Leon Palm ,  Liviu Panait

IPC: H04N1/00

CPC classification number: H04N1/00082 ,  H04N1/00005 ,  H04N1/00076 ,  H04N1/00702 ,  H04N1/00721 ,  H04N1/387

Abstract: 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.

Abstract translation: 从拍摄的角度捕获对象的图像并创建多个候选对象区域。 每个候选对象区域可能包围在图像中捕获的对象。 从多个候选对象区域中选择候选对象区域作为封闭对象。 基于所选择的候选对象区域生成对象的校正图像。 经校正的图像显示被转换为校正透视图的对象。 显示校正后的图像。