3D Object Recognition Using SOFM

3D Object Recognition Using SOFM

  • Published : 20060000

Abstract

3D object recognition independent of translation and rotation using an ultrasonic sensor array, invariant moment vectors and SOFM(Self Organizing Feature Map) neural networks is presented. Using invariant moment vectors of the acquired 16×8 pixel data of square, rectangular, cylindric and regular triangular blocks, 3D objects could be classified by SOFM neural networks. Invariant moment vectors are constant independent of translation and rotation. The recognition rates for the training and testing data were 95.91% and 92.13%, respectively.

Keywords

References

  1. V. Gabbani, S. Rocchi and V. Vignoli. 1995. Multielement Ultrasonic System for Robotic Navigation, IEEE International Conference on Robotics and Automation, pp. 3009-3014
  2. H.M. Li and L. Kleeman. 1995. A Low Sample Rate 3 D Sonar Sensor for Mobile Robots, IEEE International Conference on Robotics and Automation, pp. 3015-3020
  3. Ultrasonic Ranging System Handbook, Polaroid Corporation
  4. C. H. Teh and R.T. Chin. 1986. On Digital Approximation of Moment Invariants, Computer Vision, raphics, and Image Processing 33, pp. 318-326. M.K. Hu (l962),Visual Pattern Recognitionby Moment Invariants, IRE Trans. Information Theory, Vol. 8, pp.179-187
  5. T.K Kohonen. 1994. Self-Organization and Associative Memory, Springer Verlag