Abstract
Two-channel critically sampled spline graph filter bank (SGFB) is one of the existing solutions for signal processing on arbitrary graphs. This paper addresses an approach to modify the filter design for SGFB. Our method improves the shape of analysis filters in the spectral domain and also reduces the computational complexity for the synthesis section. Additionally, the proposed method exploits polynomial filters and does not need to compute eigendecomposition for the Laplacian matrix of the underlying graph. Numerical results show the efficacy of our approach by comparing its performance in graph signal decomposition and denoising with the existing solutions.
Similar content being viewed by others
Data Availability
The datasets generated during and/or analyzed during the current study are not publicly available due to our future works but are available from the corresponding author on reasonable request
Notes
Kron reduction is a most widely used method to reduce the graph in GSP, especially in multiscale transforms.
\(\rho (A)=\mathrm{max}\{|\lambda |\!:\!\lambda \in \varSigma (A)\}\), \(\varSigma (A)\) contains eigenvalues of matrix A.
The optimal value J and M may differ for different graphs, and an optimal value setting will be an interesting topic in the future.
Although SGFB in [5] can decompose signal in multilevel for arbitrary graphs, it does not maintain the spectral shape of the smooth graph signal after the second level and then denoising of the smooth signal is not possible.
References
A. Anis, A. Ortega, Critical sampling for wavelet filterbanks on arbitrary graphs. In: Int. Conf. on Acoustics, Speech, and Signal Process. (ICASSP) pp. 3889-3893 (2017)
S. Boyd, L. Vandenberghe, Convex Optimization (Cambridge University Press, Cambridge, 2004)
F. Dorfler, F. Bullo, Kron reduction of graphs with applications to electrical networks. IEEE Trans. Circuits Syst. I: Reg. Pap. 60(1), 150–163 (2013)
V.N. Ekambaram, G.C. Fanti, B. Ayazifar, K. Ramchandran, Multiresolution graph signal processing via circulant structures. In: Digital Signal Processing and Signal Processing Education Meeting (DSP/SPE) pp. 112-117 (2013)
V.N. Ekambaram, G.C. Fanti, B. Ayazifar, K. Ramchandran, Spline-like wavelet filterbanks for multiresolution analysis of graph-structured data. IEEE Trans. Signal Inf. Process. Netw. 1(4), 268–278 (2015)
M. Gavish, B. Nadler, R.R.Coifman, Multiscale wavelets on trees, graphs and high dimensional data: Theory and applications to semi supervised learning. In: International Conference on Machine Learning pp. 367-374 (2010)
R.A. Horn, C.R. Johnson, Matrix Analysis (Cambridge University Press, Cambridge, 1990)
J.Z. Jiang, F. Zhou, P.L. Shui, Optimization design of two-channel biorthogonal graph filter banks. Circuits Syst. Sig. Process. 35(2), 685–692 (2016)
J.Z. Jiang, C. Cheng, Q. Sun, Nonsubsampled graph filter banks: theory and distributed implementation. IEEE Trans. Signal Process. 67(15), 3938–3953 (2019)
J.Z. Jiang, D.B.H. Tay, Q. Sun, S. Ouyang, Design of nonsubsampled graph filter banks via lifting schemes. IEEE Sig. Process. Lett. 27, 441–445 (2020)
S. Li, Y. Jin, D.I. Shuman, Scalable \( M \)-channel critically sampled filter banks for graph signals. IEEE Trans. Sig. Process. 67(15), 3954–3969 (2019)
J.N. Liu, E. Isufi, G. Leus, Filter design for autoregressive moving average graph filters. IEEE Trans. Sig. Inf. Process. Over Netw. 5(1), 47–60 (2019)
S.K. Narang, A. Ortega, Perfect reconstruction two-channel wavelet filter banks for graph structured data. IEEE Trans. Sig. Process. 60(6), 2786–2799 (2012)
J. Paratte, D.I Shuman, V. Kalofolias, P. Vandergheynst, D.K. Hammond, GSPBOX: A toolbox for signal processing on graphs. ArXiv e-prints: arXiv:1408.5781, 2014
A. Sakiyama, Y. Tanaka, \( M \)-channel oversampled graph filter banks. IEEE Trans. Sig. Process. 62(14), 3578–3590 (2014)
A. Sakiyama, K. Watanabe, Y. Tanaka, A. Ortega, Two-channel critically sampled graph filter banks with spectral domain sampling. IEEE Trans. Sig. Process. 67(6), 1447–1460 (2019)
D.I. Shuman, S.K. Narang, P. Frossard, A. Ortega, P. Vandergheynst, The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains. IEEE Sig. Process. Mag. 30(3), 83–98 (2013)
D.I. Shuman, P. Vandergheynst, D. Kressner, P. Frossard, Distributed signal processing via Chebyshev polynomial approximation. IEEE Trans. Sig. Inf. Process. Over Netw. 4(4), 736–751 (2018)
G.W. Stewart, Matrix Algorithms: Basic Decompositions (Society for industrial and applied mathematics (SIAM), USA, 1998)
D.B.H. Tay, J. Zhang, Techniques for constructing biorthogonal bipartite graph filter banks. IEEE Trans. Sig. Process. 63(23), 5772–5783 (2015)
D.B.H. Tay, Z.P. Lin, Highly localised near orthogonal graph wavelets. Electron. Lett. 52(11), 966–968 (2016)
O. Teke, P.P. Vaidyanathan, Extending classical multirate signal processing theory to graphs-part II: \(M\)-channel filter banks. IEEE Trans. Sig. Process. 65(2), 423–437 (2017)
N. Tremblay, P. Borgant, Subgraph-based filterbanks for graph signals. IEEE Trans. Sig. Process. 64(15), 3827–3840 (2016)
F. Zhou, J.Z. Jiang, P.L. Shui, Optimization design of \(M\)-channel oversampled graph filter banks via successive convex approximation. Circuits Syst. Sig. Process. 38(10), 4787–4798 (2019)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Miraki, A., Saeedi-Sourck, H. A Modified Spline Graph Filter Bank. Circuits Syst Signal Process 40, 2025–2035 (2021). https://doi.org/10.1007/s00034-020-01543-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-020-01543-2