Abstract
A small flexible production cell has been built around a selectively compliant articulated robot arm. Moving on a conveyor belt, boxes marked with different labels are presented to the robot in a random order. Using a camera and a vision card, the labels on the boxes are recognized. Each one of the labels can be rotated, translated or scaled. Three different invariant feature extraction methods (signature, invariant moments of Hu and Zernike) are compared. A neural net is used to classify the labels. The task of the SCARA robot is to pick up the moving boxes and to sort them according to their labels.
Similar content being viewed by others
References
Declercq, F., Li, Z., Bauters, P., Liu, Z., and Keyser, R. D.: 1994a, A real-time vision controlled robot tracking a randomly moving object, in: Preprints IFAC Symposium on Robot Control '94, pp. 857–862.
Declercq, F., Song, Y., and Keyser, R. D.: 1994b, Continuous path and velocity control of the RTX (SCARA type) Robot, in: H. Mep (ed.), 25th Internat. Symposium on Industrial Robots, pp. 403–410.
Hu, M. K.: 1961, Pattern recognition by moment invariants, in: Proceedings IRE, Vol. 49, pp. 1428–1433.
Khotanzad, A.: 1988, Rotation invariant pattern recognition using Zernike moments, in: Ninth Internat. Conf. on Pattern Recognition, pp. 326–328.
Van Renterghem, P.: 1989, Transputers for industrial applications, Concurrency: Practice and Experience 1(2), 135–169.
Reiss, T. H.: 1991, The revised fundamental theorem of moment invariants, in: IEEE Trans. Pattern Analysis Machine Intelligence 13, 830–834.
Turan, J.: 1994, Recognition of printed Berber characters using modified rapid transform, J. Commun. 45, 24–29.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Declercq, F., De Keyser, R. Object Recognition and Selective Handling by a Robot. Journal of Intelligent and Robotic Systems 25, 121–132 (1999). https://doi.org/10.1023/A:1008088209663
Issue Date:
DOI: https://doi.org/10.1023/A:1008088209663