Two-Dimensional MAPES via Expectation Maximization and Cyclic Maximization - Spectral Analysis of Signals: The Missing Data Case - page 84

(a) (b)

5

10

15

20

25

30

5 10 15 20 25 30

(c) (d) (e)

(f) (g) (h)
FIGURE 6.4 : Modulus of the SAR images of the Slicy object obtained from a 32 × 32

data matrix with missing samples. (a) Photograph of the object (taken at 45 ◦ azimuth

angle), (b) 2-D WFFT for a 288 × 288 (not 32 × 32) data matrix, (c) 2-D complete-data

APES with M 1 = 16, (d) 2-D data missing pattern, the black stripes indicate missing

samples, (e) 2-D WFFT, (f ) 2-D GAPES with M 1 =

M 2 =

M 2 = 16, (g) 2-D MAPES-CM

with M 1 = M 2 = 16, and (h) 2-D MAPES-CM followed by 2-D rank-deficient RCF with

a20 × 20 filter-bank and a unit radius spherical constraint.