utils

utils

Functions

Name	Description
annotate_img_with_kps	Annotate an image with keypoints.
compute_ss_ds	Compute cosine similarities between the cartesian product of two arrays X and Z and
transform_keypoints	Transforms keypoints from the original image space to the aligned image space.

annotate_img_with_kps

utils.annotate_img_with_kps(bgr_img, kps, color='red', radius=2)

Annotate an image with keypoints.

Parameters: bgr_img (numpy.ndarray): The input image in BGR format. kps (numpy.ndarray): A numpy array of shape (5, 2) containing the keypoints. color (str, optional): The color of the keypoints. Default is ‘red’. Options are ‘red’, ‘blue’, ‘green’, ‘white’, ‘black’. radius (int, optional): The radius of the keypoints. Default is 2.

Returns: numpy.ndarray: The image with keypoints annotated.

compute_ss_ds

utils.compute_ss_ds(X, x_id, x_names=None, Z=None, z_id=None, z_names=None)

Compute cosine similarities between the cartesian product of two arrays X and Z and return same-source (ss) and different-source (ds) scores. If only the array X and x_id are provided, compute the cosine similarities between all pairwise combination in X. Also return the names of the files associated with each score, is x_names and z_names are provided.

Inputs

X, Z: 2d numpy arrays with embeddings (1 per line) x_id, z_id: 1d numpy arrays with identity labels x_names, z_names: 1d numpy arrays with names of files associated with the embeddings

Returns

scores :

1d numpy array with scores

y :

1d numpy arrays with ss (1) and ds (0) labels to the scores array

names :

list of tuples with names of files associated with each score

transform_keypoints

utils.transform_keypoints(keypoints, M)

Transforms keypoints from the original image space to the aligned image space.

Parameters

keypoints : numpy array

A 2D array of shape (5, 2) representing the original keypoints.

M : numpy array

The 2x3 affine transformation matrix.

Returns

:

numpy array: A 2D array of shape (5, 2) representing the transformed keypoints.