tfmri.image.ssim2d

ssim2d(img1, img2, max_val=None, filter_size=11, filter_sigma=1.5, k1=0.01, k2=0.03, name='ssim2d')[source]

Computes the structural similarity index (SSIM) between two 2D images.

This function operates on batches of multi-channel inputs and returns an SSIM value for each image in the batch.

Parameters

  • img1 – A Tensor. First batch of images. Must have rank >= 3 with shape batch_shape + [height, width, channels]. height and width must be greater than or equal to filter_size. Can have integer or floating point type, with values in the range [0, max_val].

  • img2 – A Tensor. Second batch of images. Must have rank >= 3 with shape batch_shape + [height, width, channels]. height and width must be greater than or equal to filter_size. Can have integer or floating point type, with values in the range [0, max_val].

  • max_val – The dynamic range of the images (i.e., the difference between the maximum and the minimum allowed values). Defaults to 1 for floating point input images and MAX for integer input images, where MAX is the largest positive representable number for the data type.

  • filter_size – The size of the Gaussian filter. Defaults to 11.

  • filter_sigma – The standard deviation of the Gaussian filter. Defaults to 1.5.

  • k1 – Factor used to calculate the regularization constant for the luminance term, as C1 = (k1 * max_val) ** 2. Defaults to 0.01.

  • k2 – Factor used to calculate the regularization constant for the contrast term, as C2 = (k2 * max_val) ** 2. Defaults to 0.03.

  • name – Namespace to embed the computation in.

Returns

A Tensor of type float32 and shape batch_shape containing an SSIM value for each image in the batch.

References

1

Zhou Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” in IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, April 2004, doi: 10.1109/TIP.2003.819861.