A novel fast method for computation of zernike moments based on FPGA

This paper presents a novel approach to the fast computation of Zernike moments from a digital image. Most existing fast methods for computing Zernike moments have focused on the reduction of the computational complexity of the Zernike 1-D radial polynomials by introducing their recurrence relations. Instead, in our proposed method, we focus on the reduction fo the cumulative number of the Zernike moments with many PEs (process elements) which are achieved by VHDL(VHSIC hardware description language). The architecture described above was simulated and implemented targeting Xilinx GA(gate array). In the experiments, results show the accuracy of the form for computing discrete Zernike moments and confirm that the proposed method for the fast computation of Zernike moments is much more efficient than existing fast methods in most cases.