Abstract—This paper presents an object recognition and identification system using the Harris Corner Detection method. The process starts from imported images into the system by webcam, detected image edge by canny edge detection, recognized the object by Harris Corner Detection, and separated the objects by the robot arm. Three object types; triangle, rectangular and, rigid circle are used. The results showed that the objects can be isolated 94%, 95%, and 99% correct for triangular, rectangular, and rigid circle respectively.
Index Terms—Harris Corner Detection, canny edge detection, object recognition.
Kitti Toontham and Jaruwan Toontham are with Rajamangala University of TechnologyISAN Khonkaen, Thailand (email: kitti_kkc@hotmail.com; nudiddl@hotmail.com).
Chaiyapon Thongchaisuratkul is with the King Mongkut's University of Technology North Bangkok, Thailand (email:srp@kmutnb.ac.th).
Cite: T. Kitti, T. Jaruwan, and T.Chaiyapon, "An Object Recognition and Identification System Using the Harris Corner Detection Method," International Journal of Machine Learning and Computing vol. 2, no. 4, pp. 462-465, 2012.