Image reconstruction by Krawtchouk moments via digital filter
Hicham Karmouni, Tarik Jahid, Zouhir Lakhili, Abdeslam Hmimid, Mhamed Sayyouri, Hassan Qjidaa, A. Rezzouk · 2017
In this paper we introduce a method for fast computation of Krawtchouk moments by using of cascaded digital filters. The proposed method based on the outputs of cascaded digital filters operating as accumulators are combined with a simplified Krawtchouk polynomials to form Krawtchouk moments depends on the formulation of Krawtchouk polynomials in terms of binomial functions. The theoretical framework of the proposed method is validated by an experiment on the computation of the Krawtchouk moments then the results are compared to method recursive. Experimental results show that both the proposed algorithm to compute Krawtchouk moments perform better than recursive method in term of computation speed. Finally, the performances of the computational Krawtchouk moments by proposed method in describing images were measured in terms of the image reconstruction by matrix representation.