Abstract: A three-dimensional information processing apparatus for obtaining three-dimensional information from an object having a three-dimensional shape, and performing predetermined information processing, comprises: a camera for sensing images of the object from a plurality of coordinate positions using an image sensing system having one or a plurality of optical systems. A plurality of depth information are extracted from image sensing related information sensed by the camera at the plurality of coordinate positions, and the plurality of extracted depth information are converted and unified into depth information expressed by a unified coordinate system.
Abstract: There is disclosed a method of extracting the region of a subject image from an input image including the subject image. A subject region mask for masking the region of the subject image is generated, and the contour of the subject region mask is shaped. After local regions for correcting the contour shaped by contour shaping are set on the basis of information of the contour of the subject region mask before and after contour shaping, the contour of the shaped subject region mask is corrected within the set local regions.
December 12, 1997
Date of Patent:
June 11, 2002
Canon Kabushiki Kaisha
Tatsushi Katayama, Masakazu Matsugu, Koji Hatanaka
Abstract: There is disclosed an image combining apparatus for generating a single image by combining a plurality of sensed images. When the panoramic image sensing mode is set, the image sensing angle is detected, and is stored together with a plurality of sensed image obtained in the panoramic image sensing mode. Upon combining the plurality of sensed images, a combining method is adaptively selected on the basis of the angle information.