skvideo.measure.msssim¶

skvideo.measure.msssim(referenceVideoData, distortedVideoData, method='product')[source]¶

Computes Multiscale Structural Similarity (MS-SSIM) Index. [1]

Both video inputs are compared frame-by-frame to obtain T MS-SSIM measurements on the luminance channel.

Parameters:

referenceVideoDatandarray

Reference video, ndarray of dimension (T, M, N, C), (T, M, N), (M, N, C), or (M, N), where T is the number of frames, M is the height, N is width, and C is number of channels. Here C is only allowed to be 1.

distortedVideoDatandarray

Distorted video, ndarray of dimension (T, M, N, C), (T, M, N), (M, N, C), or (M, N), where T is the number of frames, M is the height, N is width, and C is number of channels. Here C is only allowed to be 1.

methodstr

Whether to use “product” (default) or to use “sum” for combing multiple scales into the single score.

Returns:

msssim_arrayndarray

The MS-SSIM results, ndarray of dimension (T,), where T is the number of frames

References