Eigen space approach for a pose detection with range images

Abstract An application of the Pose-detection using Range-image usually uses characteristic matching of the geometrical model but this method has two problems. 1 Picking for characteristic from Range-images is difficult. 2 It is difficult to make geometrical model for a complicated shape. Recently Parametric Eigen-space Method is proposed to Pose-detect approaching such as Eigen-face. This method makes Object-Recognition, Pose-detection possible, but this Parametric Eigen-space Method has a problem that intensityimages depend on a variety of light condition therefor learning images must include variation of light condition. So we propose a Pose detection with range images by Eigenspace approach.