画像を回転させ、黒枠を切り取る

質問

私のアプリケーションです。私は画像を回転させようとしています（OpenCVとPythonを使用）。

現時点で私は、入力画像を回転させ、黒い縁でパディングし、Aを与える以下のコードを開発しました。私が欲しいのはB - 回転した画像内の可能な限り大きな領域のクロップウィンドウです。私はこれを軸に沿った boundED ボックスと呼んでいます。

これは本質的に 回転とクロップ と同じですが、その質問の回答がうまくいきません。さらに、その答えは明らかに正方形の画像にのみ有効です。私の画像は長方形です。

Aを与えるためのコード。

import cv2
import numpy as np


def getTranslationMatrix2d(dx, dy):
    """
    Returns a numpy affine transformation matrix for a 2D translation of
    (dx, dy)
    """
    return np.matrix([[1, 0, dx], [0, 1, dy], [0, 0, 1]])


def rotateImage(image, angle):
    """
    Rotates the given image about it's centre
    """

    image_size = (image.shape[1], image.shape[0])
    image_center = tuple(np.array(image_size) / 2)

    rot_mat = np.vstack([cv2.getRotationMatrix2D(image_center, angle, 1.0), [0, 0, 1]])
    trans_mat = np.identity(3)

    w2 = image_size[0] * 0.5
    h2 = image_size[1] * 0.5

    rot_mat_notranslate = np.matrix(rot_mat[0:2, 0:2])

    tl = (np.array([-w2, h2]) * rot_mat_notranslate).A[0]
    tr = (np.array([w2, h2]) * rot_mat_notranslate).A[0]
    bl = (np.array([-w2, -h2]) * rot_mat_notranslate).A[0]
    br = (np.array([w2, -h2]) * rot_mat_notranslate).A[0]

    x_coords = [pt[0] for pt in [tl, tr, bl, br]]
    x_pos = [x for x in x_coords if x > 0]
    x_neg = [x for x in x_coords if x < 0]

    y_coords = [pt[1] for pt in [tl, tr, bl, br]]
    y_pos = [y for y in y_coords if y > 0]
    y_neg = [y for y in y_coords if y < 0]

    right_bound = max(x_pos)
    left_bound = min(x_neg)
    top_bound = max(y_pos)
    bot_bound = min(y_neg)

    new_w = int(abs(right_bound - left_bound))
    new_h = int(abs(top_bound - bot_bound))
    new_image_size = (new_w, new_h)

    new_midx = new_w * 0.5
    new_midy = new_h * 0.5

    dx = int(new_midx - w2)
    dy = int(new_midy - h2)

    trans_mat = getTranslationMatrix2d(dx, dy)
    affine_mat = (np.matrix(trans_mat) * np.matrix(rot_mat))[0:2, :]
    result = cv2.warpAffine(image, affine_mat, new_image_size, flags=cv2.INTER_LINEAR)

    return result

どのように解決するのですか？

そこで、多くの解決策を検討した結果、ようやくうまくいく方法を見つけました。 アンドレイ と マグナス・ホフ について 回転した矩形の中で最大の矩形を計算する .

以下のPythonコードは、関心のあるメソッドを含んでいます。 largest_rotated_rect - と短いデモが含まれています。

import math
import cv2
import numpy as np


def rotate_image(image, angle):
    """
    Rotates an OpenCV 2 / NumPy image about it's centre by the given angle
    (in degrees). The returned image will be large enough to hold the entire
    new image, with a black background
    """

    # Get the image size
    # No that's not an error - NumPy stores image matricies backwards
    image_size = (image.shape[1], image.shape[0])
    image_center = tuple(np.array(image_size) / 2)

    # Convert the OpenCV 3x2 rotation matrix to 3x3
    rot_mat = np.vstack(
        [cv2.getRotationMatrix2D(image_center, angle, 1.0), [0, 0, 1]]
    )

    rot_mat_notranslate = np.matrix(rot_mat[0:2, 0:2])

    # Shorthand for below calcs
    image_w2 = image_size[0] * 0.5
    image_h2 = image_size[1] * 0.5

    # Obtain the rotated coordinates of the image corners
    rotated_coords = [
        (np.array([-image_w2,  image_h2]) * rot_mat_notranslate).A[0],
        (np.array([ image_w2,  image_h2]) * rot_mat_notranslate).A[0],
        (np.array([-image_w2, -image_h2]) * rot_mat_notranslate).A[0],
        (np.array([ image_w2, -image_h2]) * rot_mat_notranslate).A[0]
    ]

    # Find the size of the new image
    x_coords = [pt[0] for pt in rotated_coords]
    x_pos = [x for x in x_coords if x > 0]
    x_neg = [x for x in x_coords if x < 0]

    y_coords = [pt[1] for pt in rotated_coords]
    y_pos = [y for y in y_coords if y > 0]
    y_neg = [y for y in y_coords if y < 0]

    right_bound = max(x_pos)
    left_bound = min(x_neg)
    top_bound = max(y_pos)
    bot_bound = min(y_neg)

    new_w = int(abs(right_bound - left_bound))
    new_h = int(abs(top_bound - bot_bound))

    # We require a translation matrix to keep the image centred
    trans_mat = np.matrix([
        [1, 0, int(new_w * 0.5 - image_w2)],
        [0, 1, int(new_h * 0.5 - image_h2)],
        [0, 0, 1]
    ])

    # Compute the tranform for the combined rotation and translation
    affine_mat = (np.matrix(trans_mat) * np.matrix(rot_mat))[0:2, :]

    # Apply the transform
    result = cv2.warpAffine(
        image,
        affine_mat,
        (new_w, new_h),
        flags=cv2.INTER_LINEAR
    )

    return result


def largest_rotated_rect(w, h, angle):
    """
    Given a rectangle of size wxh that has been rotated by 'angle' (in
    radians), computes the width and height of the largest possible
    axis-aligned rectangle within the rotated rectangle.

    Original JS code by 'Andri' and Magnus Hoff from Stack Overflow

    Converted to Python by Aaron Snoswell
    """

    quadrant = int(math.floor(angle / (math.pi / 2))) & 3
    sign_alpha = angle if ((quadrant & 1) == 0) else math.pi - angle
    alpha = (sign_alpha % math.pi + math.pi) % math.pi

    bb_w = w * math.cos(alpha) + h * math.sin(alpha)
    bb_h = w * math.sin(alpha) + h * math.cos(alpha)

    gamma = math.atan2(bb_w, bb_w) if (w < h) else math.atan2(bb_w, bb_w)

    delta = math.pi - alpha - gamma

    length = h if (w < h) else w

    d = length * math.cos(alpha)
    a = d * math.sin(alpha) / math.sin(delta)

    y = a * math.cos(gamma)
    x = y * math.tan(gamma)

    return (
        bb_w - 2 * x,
        bb_h - 2 * y
    )


def crop_around_center(image, width, height):
    """
    Given a NumPy / OpenCV 2 image, crops it to the given width and height,
    around it's centre point
    """

    image_size = (image.shape[1], image.shape[0])
    image_center = (int(image_size[0] * 0.5), int(image_size[1] * 0.5))

    if(width > image_size[0]):
        width = image_size[0]

    if(height > image_size[1]):
        height = image_size[1]

    x1 = int(image_center[0] - width * 0.5)
    x2 = int(image_center[0] + width * 0.5)
    y1 = int(image_center[1] - height * 0.5)
    y2 = int(image_center[1] + height * 0.5)

    return image[y1:y2, x1:x2]


def demo():
    """
    Demos the largest_rotated_rect function
    """

    image = cv2.imread("lenna_rectangle.png")
    image_height, image_width = image.shape[0:2]

    cv2.imshow("Original Image", image)

    print "Press [enter] to begin the demo"
    print "Press [q] or Escape to quit"

    key = cv2.waitKey(0)
    if key == ord("q") or key == 27:
        exit()

    for i in np.arange(0, 360, 0.5):
        image_orig = np.copy(image)
        image_rotated = rotate_image(image, i)
        image_rotated_cropped = crop_around_center(
            image_rotated,
            *largest_rotated_rect(
                image_width,
                image_height,
                math.radians(i)
            )
        )

        key = cv2.waitKey(2)
        if(key == ord("q") or key == 27):
            exit()

        cv2.imshow("Original Image", image_orig)
        cv2.imshow("Rotated Image", image_rotated)
        cv2.imshow("Cropped Image", image_rotated_cropped)

    print "Done"


if __name__ == "__main__":
    demo()

<イグ

単純に この画像 (正方形でない画像でも動作することを示すために切り取ってあります) を上記のファイルと同じディレクトリに置いて、実行してください。