Recognition of patterns without feature extraction by GRNN


8th International Conference on Adaptive and Natural Computing Algorithms, ICANNGA 2007, Warszawa, Poland, 11 - 14 April 2007, pp.161-168 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1007/978-3-540-71629-7_19
  • City: Warszawa
  • Country: Poland
  • Page Numbers: pp.161-168
  • Yıldız Technical University Affiliated: Yes


Automatic pattern recognition is a very important task in many applications such as image segmentation, object detection, etc. This work aims to find a new approach to automatically recognize patterns such as 3D objects and handwritten digits based on a database using General Regression Neural Networks (GRNN). The designed system can be used for both 3D object recognition from 2D poses of the object and handwritten digit recognition applications. The system does not require any preprocessing and feature extraction stage before the recognition. Simulation results show that pattern recognition by GRNN improves the recognition rate considerably in comparison to other neural network structures and has shown better recognition rates and much faster training times than that of Radial Basis Function and Multilayer Perceptron networks for the same applications. © Springer-Verlag Berlin Heidelberg 2007.