normalize_var¶
-
menpo.feature.
normalize_var
(pixels, mode='all', error_on_divide_by_zero=True)[source]¶ Normalize the pixels to be mean centred and normalize according to the variance. The
mode
parameter selects whether the normalisation is computed across all pixels in the image or per-channel.- Parameters
pixels (
Image
or subclass or(C, X, Y, ..., Z)
ndarray) – Either the image object itself or an array with the pixels. The first dimension is interpreted as channels. This means an N-dimensional image is represented by an N+1 dimensional array.mode (
{all, per_channel}
, optional) – Ifall
, the normalization is over all channels. Ifper_channel
, each channel individually is mean centred and normalized in variance.error_on_divide_by_zero (bool, optional) – If
True
, will raise aValueError
on dividing by zero. IfFalse
, will merely raise a warning and only those values with non-zero denominators will be normalized.
- Returns
pixels (
Image
or subclass or(X, Y, ..., Z, C)
ndarray) – A normalized copy of the image that was passed in.- Raises
ValueError – If any of the denominators are 0 and
error_on_divide_by_zero
isTrue
.