Skip to main content

Table 1 Size of the variables involved in the definition of the MLP, both in the degradation and the restoration processes

From: Boundary reconstruction process of a TV-based neural net without prior conditions

Degradation

size{x}

size{h}

size{H a }

size{H a x}

size{ytru}

L × 1

M × 1

L ̃ × L

L ̃ × 1

L ̃ × 1

L = [L1 × L2]

M = 2 B 1 + 1 × 2 B 2 + 1

L ̃ = ( L 1 + 2 B 1 ) × ( L 2 + 2 B 2 )

Truncated image ytru is defined in the support FOV = L 1 - 2 B 1 × L 2 - 2 B 2 and the rest are zeros up to the size L ̃

Restoration

size{dξ}, size{dμ}

size D a ξ , size D a μ

size D a ξ x , size D a μ x

size trunc D a ξ x , size trunc D a μ x

N × 1

U × L

U × 1

U × 1

N = [N1×N2]

U = [(L1+N1-1) × (L2+N2-1)]

Truncated images D a ξ x and D a μ x are defined in the support [(L1-N1+1) × (L2-N2+1)] and the rest are zeros up to the size U