Image quality measurement based on local amplitude and phase spectra
A quality measurement, local technology, applied in the field of image processing, can solve the problems of subjective image quality assessment, blurring and so on without reporting
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] In an offline fashion, the ISA bases are pre-learned independently of the image whose quality will be predicted. In an exemplary embodiment, an 8x8 ISA is performed, resulting in 14 subgroups. Each subgroup contains four bases. There are 56 bases in total. The basis defines an orthogonal (incomplete) transformation. ISA transforms linear matrix computations like 2D DCT. Thus, each 8x8 image patch produces 56 ISA transform coefficients, resulting in fourteen four-dimensional ISA transform coefficient vectors. Note that training on different datasets may result in slightly different ISA bases, however, the performance of our metric is insensitive to such variations. Each basis is vectorized as a row vector, fourteen bases yielding a 56x64 matrix W. If each 8x8 image patch is vectorized as a column vector Then the ISA transform is given by:
[0031] s → = W x →
[0...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 