Object Recognition with Kinect Sensor

This paper proposes a new algorithm for object recognition with high precision and an efficient execution time using the Kinect sensor. The proposed algorithm is based on geometric hashing and provides a more detailed geometric description of objects that can be further used to identify object parts or other information localized on the object´s surface. The algorithm was tested on a dataset that consists of 11 reference objects and 32 snapshots. The obtained precision was 81%.