A synergetic prototype vectors fusion reconstruction classification algorithm based on nonsubsampled contourlet transform

The selection of synergetic prototype vectors of synergetic approach is very important to pattern recognition, which set the tone for the recognition performance of synergetic approach. Contourlet is a new image representation scheme which has the directionality and anisotropy. In this paper, the characteristic of contourlet transform is analyzed firstly. Then a new fusion method for prototype vectors generation is proposed based on contourlet transform. Finally, the coefficients structure and fusion procedure are discussed and analyzed. Experiment results show that the method of prototype vectors generation is effective and it improves the recognition rate greatly.