SortBlur

class tools.sort.sort_methods.SortBlur(arguments: Namespace, is_group: bool = False)

Bases: SortMethod

Sort images by blur or blur-fft amount

Parameters:

arguments (Namespace) – The command line arguments passed to the sort process
is_group (bool) – Set to True if this class is going to be called exclusively for binning. Default: False

Attributes Summary

`bin_names`	The name of each created bin, if they exist, otherwise an empty list
`binned`	List of bins (list) containing the filenames belonging to the bin.
`loader_type`	The loader that this sorter uses
`sorted_filelist`	List of sorted filenames for given sorter in a single list.

Methods Summary

`binning`()	Create bins to split linearly from the lowest to the highest sample value
`estimate_blur`(image[, alignments])	Estimate the amount of blur an image has with the variance of the Laplacian.
`estimate_blur_fft`(image[, alignments])	Estimate the amount of blur a fft filtered image has.
`score_image`(filename, image, alignments)	Score a single image for blur or blur-fft and add the result to `_result`
`sort`()	Sort by metric score.

Attributes Documentation

bin_names: The name of each created bin, if they exist, otherwise an empty list

binned: List of bins (list) containing the filenames belonging to the bin. The binning process is called when this property is first accessed

loader_type

The loader that this sorter uses

Type:: [“face”, “meta”, “all”]

sorted_filelist: List of sorted filenames for given sorter in a single list. The sort process is called when this property is first accessed

Methods Documentation

binning() → list[list[str]]

Create bins to split linearly from the lowest to the highest sample value

Return type:: List of bins of filenames

estimate_blur(image: ndarray, alignments=None) → float

Estimate the amount of blur an image has with the variance of the Laplacian. Normalize by pixel number to offset the effect of image size on pixel gradients & variance.

Parameters:

image (ndarray) – The face image to calculate blur for
alignments – The metadata for the face image or None if no metadata is available. If metadata is provided the face will be masked by the “components” mask prior to calculating blur. Default:None

Return type:

The estimated blur score for the face

estimate_blur_fft(image: np.ndarray, alignments: PNGAlignments | None = None) → float

Estimate the amount of blur a fft filtered image has.

Parameters:

image (np.ndarray) – Use Fourier Transform to analyze the frequency characteristics of the masked face using 2D Discrete Fourier Transform (DFT) filter to find the frequency domain. A mean value is assigned to the magnitude spectrum and returns a blur score. Adapted from https://www.pyimagesearch.com/2020/06/15/ opencv-fast-fourier-transform-fft-for-blur-detection-in-images-and-video-streams/
alignments (PNGAlignments | None) – The metadata for the face image or None if no metadata is available. If metadata is provided the face will be masked by the “components” mask prior to calculating blur. Default:None

Return type:

The estimated fft blur score for the face

score_image(filename: str, image: np.ndarray | None, alignments: PNGAlignments | None) → None

Score a single image for blur or blur-fft and add the result to _result

Parameters:

filename (str) – The filename of the currently processing image
image (np.ndarray | None) – A face image loaded from disk
alignments (PNGAlignments | None) – The alignments dictionary for the aligned face or None

Return type:

None

sort() → None

Sort by metric score. Order in reverse for distance sort.

Return type:: None

binning() → list[list[str]]

Create bins to split linearly from the lowest to the highest sample value

Return type:: List of bins of filenames

estimate_blur(image: ndarray, alignments=None) → float

Estimate the amount of blur an image has with the variance of the Laplacian. Normalize by pixel number to offset the effect of image size on pixel gradients & variance.

Parameters:

image (ndarray) – The face image to calculate blur for
alignments – The metadata for the face image or None if no metadata is available. If metadata is provided the face will be masked by the “components” mask prior to calculating blur. Default:None

Return type:

The estimated blur score for the face

estimate_blur_fft(image: np.ndarray, alignments: PNGAlignments | None = None) → float

Estimate the amount of blur a fft filtered image has.

Parameters:

image (np.ndarray) – Use Fourier Transform to analyze the frequency characteristics of the masked face using 2D Discrete Fourier Transform (DFT) filter to find the frequency domain. A mean value is assigned to the magnitude spectrum and returns a blur score. Adapted from https://www.pyimagesearch.com/2020/06/15/ opencv-fast-fourier-transform-fft-for-blur-detection-in-images-and-video-streams/
alignments (PNGAlignments | None) – The metadata for the face image or None if no metadata is available. If metadata is provided the face will be masked by the “components” mask prior to calculating blur. Default:None

Return type:

The estimated fft blur score for the face

score_image(filename: str, image: np.ndarray | None, alignments: PNGAlignments | None) → None

Score a single image for blur or blur-fft and add the result to _result

Parameters:

filename (str) – The filename of the currently processing image
image (np.ndarray | None) – A face image loaded from disk
alignments (PNGAlignments | None) – The alignments dictionary for the aligned face or None

Return type:

None

sort() → None

Sort by metric score. Order in reverse for distance sort.

Return type:: None