random_warp.py

import numpy as np
import cv2

random_transform_args = {
    'rotation_range': 10,
    'zoom_range': 0.05,
    'shift_range': 0.05,
    'random_flip': 0.4,
}

def get_training_data(images, batch_size):
    indices = np.random.randint(len(images), size=batch_size)
    for i, index in enumerate(indices):
        image = images[index]
        image = random_transform(image, **random_transform_args)
        warped_img, target_img = random_warp(image)

        if i == 0:
            warped_images = np.empty((batch_size,) + warped_img.shape, warped_img.dtype)
            target_images = np.empty((batch_size,) + target_img.shape, warped_img.dtype)

        warped_images[i] = warped_img
        target_images[i] = target_img

    return warped_images, target_images

def random_transform(image, rotation_range, zoom_range, shift_range, random_flip):
    h, w = image.shape[0:2]
    rotation = np.random.uniform(-rotation_range, rotation_range)
    scale = np.random.uniform(1 - zoom_range, 1 + zoom_range)
    tx = np.random.uniform(-shift_range, shift_range) * w
    ty = np.random.uniform(-shift_range, shift_range) * h
    mat = cv2.getRotationMatrix2D((w // 2, h // 2), rotation, scale)
    mat[:, 2] += (tx, ty)
    result = cv2.warpAffine(image, mat, (w, h), borderMode=cv2.BORDER_REPLICATE)
    if np.random.random() < random_flip:
        result = result[:, ::-1]
    return result

# get pair of random warped images from aligened face image
def random_warp(image):
    assert image.shape == (256, 256, 3)
    range_ = np.linspace(128 - 80, 128 + 80, 5)
    mapx = np.broadcast_to(range_, (5, 5))
    mapy = mapx.T

    mapx = mapx + np.random.normal(size=(5, 5), scale=5)
    mapy = mapy + np.random.normal(size=(5, 5), scale=5)

    interp_mapx = cv2.resize(mapx, (80, 80))[8:72, 8:72].astype('float32')
    interp_mapy = cv2.resize(mapy, (80, 80))[8:72, 8:72].astype('float32')

    warped_image = cv2.remap(image, interp_mapx, interp_mapy, cv2.INTER_LINEAR)

    src_points = np.stack([mapx.ravel(), mapy.ravel()], axis=-1)
    dst_points = np.mgrid[0:65:16, 0:65:16].T.reshape(-1, 2)
    mat = umeyama(src_points, dst_points, True)[0:2]

    target_image = cv2.warpAffine(image, mat, (64, 64))

    return warped_image, target_image


def umeyama(src, dst, estimate_scale):
    """Estimate N-D similarity transformation with or without scaling.
    Parameters
    ----------
    src : (M, N) array
        Source coordinates.
    dst : (M, N) array
        Destination coordinates.
    estimate_scale : bool
        Whether to estimate scaling factor.
    Returns
    -------
    T : (N + 1, N + 1)
        The homogeneous similarity transformation matrix. The matrix contains
        NaN values only if the problem is not well-conditioned.
    References
    ----------
    .. [1] "Least-squares estimation of transformation parameters between two
            point patterns", Shinji Umeyama, PAMI 1991, DOI: 10.1109/34.88573
    """

    num = src.shape[0]
    dim = src.shape[1]

    # Compute mean of src and dst.
    src_mean = src.mean(axis=0)
    dst_mean = dst.mean(axis=0)

    # Subtract mean from src and dst.
    src_demean = src - src_mean
    dst_demean = dst - dst_mean

    # Eq. (38).
    A = np.dot(dst_demean.T, src_demean) / num

    # Eq. (39).
    d = np.ones((dim,), dtype=np.double)
    if np.linalg.det(A) < 0:
        d[dim - 1] = -1

    T = np.eye(dim + 1, dtype=np.double)

    U, S, V = np.linalg.svd(A)

    # Eq. (40) and (43).
    rank = np.linalg.matrix_rank(A)
    if rank == 0:
        return np.nan * T
    elif rank == dim - 1:
        if np.linalg.det(U) * np.linalg.det(V) > 0:
            T[:dim, :dim] = np.dot(U, V)
        else:
            s = d[dim - 1]
            d[dim - 1] = -1
            T[:dim, :dim] = np.dot(U, np.dot(np.diag(d), V))
            d[dim - 1] = s
    else:
        T[:dim, :dim] = np.dot(U, np.dot(np.diag(d), V.T))

    if estimate_scale:
        # Eq. (41) and (42).
        scale = 1.0 / src_demean.var(axis=0).sum() * np.dot(S, d)
    else:
        scale = 1.0

    T[:dim, dim] = dst_mean - scale * np.dot(T[:dim, :dim], src_mean.T)
    T[:dim, :dim] *= scale

    return T