skimage2.measure.blur_effect

skimage2.measure.blur_effect(image, h_size=11, channel_axis=None, reduce_func=<function max>)

Compute a metric that indicates the strength of blur in an image (0 for no blur, 1 for maximal blur).

Parameters:

imagendarray

RGB or grayscale nD image. The input image is converted to grayscale before computing the blur metric.

h_sizeint, optional

Size of the re-blurring filter.

channel_axisint or None, optional

If None, the image is assumed to be grayscale (single-channel). Otherwise, this parameter indicates which axis of the array corresponds to color channels.

reduce_funccallable, optional

Function used to calculate the aggregation of blur metrics along all axes. If set to None, the entire list is returned, where the i-th element is the blur metric along the i-th axis.

Returns:

blurfloat (0 to 1) or list of floats

Blur metric: by default, the maximum of blur metrics along all axes.

Notes

h_size must keep the same value in order to compare results between images. Most of the time, the default size (11) is enough. This means that the metric can clearly discriminate blur up to an average 11x11 filter; if blur is higher, the metric still gives good results but its values tend towards an asymptote.

References

[1]

Frederique Crete, Thierry Dolmiere, Patricia Ladret, and Marina Nicolas “The blur effect: perception and estimation with a new no-reference perceptual blur metric” Proc. SPIE 6492, Human Vision and Electronic Imaging XII, 64920I (2007) https://hal.archives-ouvertes.fr/hal-00232709 DOI:10.1117/12.702790