pyiqa.archs.fsim_arch
=====================

.. py:module:: pyiqa.archs.fsim_arch

.. autoapi-nested-parse::

   FSIM Metric

   @article{zhang2011fsim,
     title={FSIM: A feature similarity index for image quality assessment},
     author={Zhang, Lin and Zhang, Lei and Mou, Xuanqin and Zhang, David},
     journal={IEEE transactions on Image Processing},
     volume={20},
     number={8},
     pages={2378--2386},
     year={2011},
     publisher={IEEE}
   }

   Created by: https://github.com/photosynthesis-team/piq/blob/master/piq/fsim.py
   Modified by: Jiadi Mo (https://github.com/JiadiMo)

   Refer to:
       Official matlab code from https://www4.comp.polyu.edu.hk/~cslzhang/IQA/FSIM/Files/FeatureSIM.m
       PIQA from https://github.com/francois-rozet/piqa/blob/master/piqa/fsim.py







Module Contents
---------------

.. py:function:: fsim(x: torch.Tensor, y: torch.Tensor, chromatic: bool = True, scales: int = 4, orientations: int = 4, min_length: int = 6, mult: int = 2, sigma_f: float = 0.55, delta_theta: float = 1.2, k: float = 2.0) -> torch.Tensor

   Compute Feature Similarity Index Measure for a batch of images.
   :param - x: An input tensor. Shape :math:`(N, C, H, W)`.
   :param - y: A target tensor. Shape :math:`(N, C, H, W)`.
   :param - chromatic: Flag to compute FSIMc, which also takes into account chromatic components
   :param - scales: Number of wavelets used for computation of phase congruensy maps
   :param - orientations: Number of filter orientations used for computation of phase congruensy maps
   :param - min_length: Wavelength of smallest scale filter
   :param - mult: Scaling factor between successive filters
   :param - sigma_f: Ratio of the standard deviation of the Gaussian describing the log Gabor filter's
   :param transfer function in the frequency domain to the filter center frequency.:
   :param - delta_theta: Ratio of angular interval between filter orientations and the standard deviation
   :param of the angular Gaussian function used to construct filters in the frequency plane.:
   :param - k: No of standard deviations of the noise energy beyond the mean at which we set the noise
               threshold  point, below which phase congruency values get penalized.

   :returns:

             - Index of similarity between two images. Usually in [0, 1] interval.
             Can be bigger than 1 for predicted :math:`x` images with higher contrast than the original ones.

   .. rubric:: References

   L. Zhang, L. Zhang, X. Mou and D. Zhang, "FSIM: A Feature Similarity Index for Image Quality Assessment,"
   IEEE Transactions on Image Processing, vol. 20, no. 8, pp. 2378-2386, Aug. 2011, doi: 10.1109/TIP.2011.2109730.
   https://ieeexplore.ieee.org/document/5705575


.. py:class:: FSIM(chromatic: bool = True, scales: int = 4, orientations: int = 4, min_length: int = 6, mult: int = 2, sigma_f: float = 0.55, delta_theta: float = 1.2, k: float = 2.0)

   Bases: :py:obj:`torch.nn.Module`


   :param - chromatic: Flag to compute FSIMc, which also takes into account chromatic components
   :param - scales: Number of wavelets used for computation of phase congruensy maps
   :param - orientations: Number of filter orientations used for computation of phase congruensy maps
   :param - min_length: Wavelength of smallest scale filter
   :param - mult: Scaling factor between successive filters
   :param - sigma_f: Ratio of the standard deviation of the Gaussian describing the log Gabor filter's
   :param transfer function in the frequency domain to the filter center frequency.:
   :param - delta_theta: Ratio of angular interval between filter orientations and the standard deviation
   :param of the angular Gaussian function used to construct filters in the frequency plane.:
   :param - k: No of standard deviations of the noise energy beyond the mean at which we set the noise
               threshold  point, below which phase congruency values get penalized.

   .. rubric:: References

   L. Zhang, L. Zhang, X. Mou and D. Zhang, "FSIM: A Feature Similarity Index for Image Quality Assessment,"
   IEEE Transactions on Image Processing, vol. 20, no. 8, pp. 2378-2386, Aug. 2011, doi: 10.1109/TIP.2011.2109730.
   https://ieeexplore.ieee.org/document/5705575


   .. py:method:: forward(X: torch.Tensor, Y: torch.Tensor) -> torch.Tensor

      Computation of FSIM as a loss function.
      :param - x: An input tensor. Shape :math:`(N, C, H, W)`.
      :param - y: A target tensor. Shape :math:`(N, C, H, W)`.

      :returns:

                - Value of FSIM loss to be minimized in [0, 1] range.