Sparse Regularization Based on Orthogonal Tensor Dictionary Learning for Inverse Problems

Figure 13

(a) Real seismic data. (b) Noisy real seismic data (SNR = 2.48). Denoising results by (c) K-SVD (SNR = 16.58), (d) orthogonal DL algorithm (SNR = 17.55), and (e) the proposed method (SNR = 19.13).

(a)

(b)

(c)

(d)

(e)