Abstract
This paper presents a model of a system for invariant object recognition, which consists of five stages. The first stage shifts the object so that the centroid of the object coincides with the center of the image plane. The second stage is an application of the polar-coordinate transforms used to obtain N-dimensional vectors-representations of the input object. In this stage, any rotation of the input object becomes a cyclic shift of the output value of this stage. The third stage employs CT (Certain Transform), a class of shift-invariant transformations to provide invariant representations for cyclically shifted inputs. The next stage normalizes the outputs of the previous stage to obtain scale invariance. The final stage realizes a classification.
[1] Eason G., Noble B., Sneddon I.N., On certain integrals of Lipschitz-Hankel type involving products of Bessel functions, Phil. Trans. Roy. Soc. London, 529–551, 1955 10.1098/rsta.1955.0005Search in Google Scholar
[2] Ren F.X., Huang J., Jiang R., Klette, R., ”General traffic sign recognition by feature matching”, Image and Vision Computing New Zealand, 2009. IVCNZ’ 09. 24th International Conference, 23–25, 409–414, 2009 10.1109/IVCNZ.2009.5378370Search in Google Scholar
[3] Ruta A., Li Y., Liu X., ”Detection, Tracking and Recognition of Traffic Signs from Video Input,” Intelligent Transportation Systems, 2008. ITSC 2008. 11th International IEEE Conference, 55–60, 12–15 Oct. 2008 10.1109/ITSC.2008.4732535Search in Google Scholar
[4] Shams S., Translation-, Rotation-, Scale-, and Distortion- Invariant Object Recognition Through Self-Organization, Int. J. Neur. Syst. 8, 173–179, 1997 http://dx.doi.org/10.1142/S012906579700019710.1142/S0129065797000197Search in Google Scholar
[5] Turán J., Fast translation invariant transform and their applications. Košice: Elfa, 1999 Search in Google Scholar
[6] Turán J., Acoustic Object Recognition with Use of Rapid Transform, First Japanese-Czechoslovak Joint Seminar on Aplied Electromagnetics, 87–91, 1992 Search in Google Scholar
[7] Turán J., Recognition of Printed Berber Characters Using Modified Rapid Transform, J. Of Communications XLV, 24–27, 1994 Search in Google Scholar
[8] Verma, B. Recognition of Rotating Images Using an Automatic Feature Extraction Technique and Neural Networks, Int. J. Neur. Syst., 8, 201–207, 1997 http://dx.doi.org/10.1142/S012906579700021510.1142/S0129065797000215Search in Google Scholar PubMed
[9] You S.D, Ford G.E., Connectionist Model for Object Recognition, Applications of Artifical Neural Networks III, 1709, 200–207, 1992 10.1117/12.139998Search in Google Scholar
[10] You S.D, Ford G.E., Object Recognition Based On Projection, Proceedings of 1993 International Joint Conference on Neural Networks, 31–36, 1993 Search in Google Scholar
[11] You S.D, Ford G.E., Network model for Invariant Object Recognition and Rotation Angle Estimation, International Joint Conference on Neural Networks, 1993 Search in Google Scholar
© 2012 Versita Warsaw
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.
