Sparse Signal Representation for a single-image Super Resolution
The research on image Statistics gives a forward step to represent the image patch in a better way
Versandfertig in 6-10 Tagen
26,99 €
inkl. MwSt.
PAYBACK Punkte
13 °P sammeln!
Many effective approaches designed to solve ill-posed and ill-conditioned problem had deficiencies to fulfill the needs of point spread function (PSF), which is hard to get into the practical situation all the time. So this project introduces a method called as Sparse signal representation for a single-image Super Resolution. The research on image Statistics gives a forward step to represent the image patches in a better way, as a sparse linear combination of elements, which are chosen from complete dictionary. From the coefficients of the sparse representation are utilized to construct the hi...
Many effective approaches designed to solve ill-posed and ill-conditioned problem had deficiencies to fulfill the needs of point spread function (PSF), which is hard to get into the practical situation all the time. So this project introduces a method called as Sparse signal representation for a single-image Super Resolution. The research on image Statistics gives a forward step to represent the image patches in a better way, as a sparse linear combination of elements, which are chosen from complete dictionary. From the coefficients of the sparse representation are utilized to construct the high-resolution output image. Here it trains two dictionaries jointly for the low-and high-resolution image patch, which produces two individual dictionary and it shows that the sparse representations for low- and high-resolution is same. To produce a high resolution image patch, the sparse representation can put together two trained dictionaries of the low- and the high-resolution image patch. A large amount of image patch pair are sampled here, by decreasing the computational cost significantly.
Andere Kunden interessierten sich für
