使用OpenCV和SIFT/SURF校正扫描图像以匹配原始图像

Question

我有一份数字形式的原始页面和几份相同页面的扫描版本。我的目标是将扫描页面倾斜校正，使其尽可能地与原始页面匹配。我知道我可以使用概率霍夫变换（Probabilistic Hough Transform），如这里所述，来修复旋转，但扫描纸张也因为某些人将页面缩放到不同的纸张格式而大小不同。我认为在OpenCV中使用findHomography()函数和SIFT/SURF的关键点组合正是我需要解决这个问题的方法。然而，我的deskew()函数就是无法工作。

我的大部分代码来自以下两个来源： http://www.learnopencv.com/homography-examples-using-opencv-python-c/ 和 http://docs.opencv.org/3.1.0/d1/de0/tutorial_py_feature_homography.html。

import numpy as np
import cv2
from matplotlib import pyplot as plt


# FIXME: doesn't work
def deskew():
    im_out = cv2.warpPerspective(img1, M, (img2.shape[1], img2.shape[0]))
    plt.imshow(im_out, 'gray')
    plt.show()


# resizing images to improve speed
factor = 0.4
img1 = cv2.resize(cv2.imread("image.png", 0), None, fx=factor, fy=factor, interpolation=cv2.INTER_CUBIC)
img2 = cv2.resize(cv2.imread("imageSkewed.png", 0), None, fx=factor, fy=factor, interpolation=cv2.INTER_CUBIC)

surf = cv2.xfeatures2d.SURF_create()
kp1, des1 = surf.detectAndCompute(img1, None)
kp2, des2 = surf.detectAndCompute(img2, None)

FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1, des2, k=2)

# store all the good matches as per Lowe's ratio test.
good = []
for m, n in matches:
    if m.distance < 0.7 * n.distance:
        good.append(m)

MIN_MATCH_COUNT = 10
if len(good) > MIN_MATCH_COUNT:
    src_pts = np.float32([kp1[m.queryIdx].pt for m in good
                          ]).reshape(-1, 1, 2)
    dst_pts = np.float32([kp2[m.trainIdx].pt for m in good
                          ]).reshape(-1, 1, 2)

    M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
    matchesMask = mask.ravel().tolist()
    h, w = img1.shape
    pts = np.float32([[0, 0], [0, h - 1], [w - 1, h - 1], [w - 1, 0]]).reshape(-1, 1, 2)
    dst = cv2.perspectiveTransform(pts, M)

    deskew()

    img2 = cv2.polylines(img2, [np.int32(dst)], True, 255, 3, cv2.LINE_AA)
else:
    print("Not  enough  matches are found   -   %d/%d" % (len(good), MIN_MATCH_COUNT))
    matchesMask = None

# show matching keypoints
draw_params = dict(matchColor=(0, 255, 0),  # draw  matches in  green   color
                   singlePointColor=None,
                   matchesMask=matchesMask,  # draw only    inliers
                   flags=2)
img3 = cv2.drawMatches(img1, kp1, img2, kp2, good, None, **draw_params)
plt.imshow(img3, 'gray')
plt.show()

- dev-random

---

我在这里做了类似的事情（https://stackoverflow.com/questions/32435488/align-x-ray-images-find-rotation-rotate-and-crop/32441230#32441230），可能会有所帮助。 - Martin Evans

@MartinEvans 谢谢，那个方法很相似，但我需要尽可能地将倾斜的图像与原始图像对齐。我刚刚找到了这个 Mathlab 教程，它完美地解决了我的问题，但不幸的是我无法理解第五步。你知道如何修改我的示例代码使其正常工作吗？ - dev-random

Answer 1

原来我离解决问题很近了。 以下是我的代码工作版本:

import numpy as np
import cv2
from matplotlib import pyplot as plt
import math


def deskew():
    im_out = cv2.warpPerspective(skewed_image, np.linalg.inv(M), (orig_image.shape[1], orig_image.shape[0]))
    plt.imshow(im_out, 'gray')
    plt.show()

orig_image = cv2.imread(r'image.png', 0)
skewed_image = cv2.imread(r'imageSkewed.png', 0)

surf = cv2.xfeatures2d.SURF_create(400)
kp1, des1 = surf.detectAndCompute(orig_image, None)
kp2, des2 = surf.detectAndCompute(skewed_image, None)

FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1, des2, k=2)

# store all the good matches as per Lowe's ratio test.
good = []
for m, n in matches:
    if m.distance < 0.7 * n.distance:
        good.append(m)

MIN_MATCH_COUNT = 10
if len(good) > MIN_MATCH_COUNT:
    src_pts = np.float32([kp1[m.queryIdx].pt for m in good
                          ]).reshape(-1, 1, 2)
    dst_pts = np.float32([kp2[m.trainIdx].pt for m in good
                          ]).reshape(-1, 1, 2)

    M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)

    # see https://ch.mathworks.com/help/images/examples/find-image-rotation-and-scale-using-automated-feature-matching.html for details
    ss = M[0, 1]
    sc = M[0, 0]
    scaleRecovered = math.sqrt(ss * ss + sc * sc)
    thetaRecovered = math.atan2(ss, sc) * 180 / math.pi
    print("Calculated scale difference: %.2f\nCalculated rotation difference: %.2f" % (scaleRecovered, thetaRecovered))

    deskew()

else:
    print("Not  enough  matches are found   -   %d/%d" % (len(good), MIN_MATCH_COUNT))
    matchesMask = None

- dev-random

Answer 2

这是一个与OpenCV 2.4.x兼容的实现。上面的答案使用了OpenCV 3.x：

import numpy as np
import cv2
import os
import errno
from os import path

SRC_FOLDER = "images/source/{YOUR_SOURCE_IMAGE_DIR}"
OUT_FOLDER = "images/output"
DETECTOR = cv2.SURF()

FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
MATCHER = cv2.FlannBasedMatcher(index_params, search_params)
MIN_MATCH_COUNT = 10


def deskew(base_image_shape, skewed_image, homography):
    return cv2.warpPerspective(skewed_image, np.linalg.inv(homography), (base_image_shape[1], base_image_shape[0]))


def compute_points_and_descriptors(image):
    """
    :param image: numpy.ndarray
    :return: keypoints, descriptors
    """
    gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    eq_hist_gray_image = cv2.equalizeHist(gray_image)
    return DETECTOR.detectAndCompute(eq_hist_gray_image, None)


def find_homography(base_keypoints, base_descriptors, skewed_image):
    skewed_keypoints, skewed_descriptors = compute_points_and_descriptors(skewed_image)
    matches = MATCHER.knnMatch(base_descriptors, skewed_descriptors, k=2)
    good = []
    for m, n in matches:
        if m.distance < 0.7 * n.distance:
            good.append(m)
    # print(len(good))
    if len(good) < MIN_MATCH_COUNT: return None

    base_pts = np.float32([base_keypoints[m.queryIdx].pt for m in good
                          ]).reshape(-1, 1, 2)
    skewed_pts = np.float32([skewed_keypoints[m.trainIdx].pt for m in good
                          ]).reshape(-1, 1, 2)

    homography, _ = cv2.findHomography(base_pts, skewed_pts, cv2.RANSAC, 5.0)
    return homography


if __name__ == "__main__":
    src_contents = os.walk(SRC_FOLDER)
    dirpath, _, fnames = src_contents.next()

    image_dir = os.path.split(dirpath)[-1]
    output_dir = os.path.join(OUT_FOLDER, image_dir)

    try:
        os.makedirs(output_dir)
    except OSError as exception:
        if exception.errno != errno.EEXIST:
            raise

    print "Processing '" + image_dir + "' folder..."

    image_files = sorted([os.path.join(dirpath, name) for name in fnames])
    img_stack = [cv2.imread(name) for name in image_files]

    base_image = img_stack[0]
    base_image_shape = base_image.shape
    base_keypoints, base_descriptors = compute_points_and_descriptors(base_image)
    cv2.imwrite(path.join(output_dir, "output0.png"), base_image)
    for ix, image in enumerate(img_stack[1:]):
        homography = find_homography(base_keypoints, base_descriptors, image)
        deskewed_image = deskew(base_image_shape, image, homography)
        cv2.imwrite(path.join(output_dir, "output{}.png".format(ix+1)), deskewed_image)

    print("Done")

- orangepips