Research Article
Block-Based MAP Superresolution Using Feature-Driven Prior Model
Algorithm 1
The summary of AR-BMSFP Algorithm.
Objective: Estimate super-resolution . | Input: | Low-resolution images sequence , Motion matrix , Border-expansion width , Total rows of block , Total | columns of block | Initialization: Estimate initial image with shift and add Algorithm | Splitting: | Split the initial image into blocks | Expand each block pixels width and obtain | Estimate , and for each block | Compress into according to | Optimization: | Form the block cost function using (18) | Optimize with Scaled Conjugate Gradients (SCG) and initial block obtaining the overlapped super-resolution | block | Recombination: | Cut border of with pixels width, obtaining super-resolution block ; Combine all super-resolution blocks obtaining | the result image | Result: The output is . |
|