使用 OpenCV 和 SIFT/SURF 校正扫描图像以匹配原始图像

问题描述

我有一个数字形式的原始页面和同一页面的多个扫描版本.我的目标是对扫描的页面进行纠偏，使其尽可能与原始页面匹配.我知道我可以使用

解决方案

原来我非常接近解决自己的问题.这是我的代码的工作版本:

将 numpy 导入为 np导入简历2从 matplotlib 导入 pyplot 作为 plt导入数学def 纠偏():im_out = cv2.warpPerspective(skewed_image, np.linalg.inv(M), (orig_image.shape[1], orig_image.shape[0]))plt.imshow(im_out, '灰色')plt.show()orig_image = cv2.imread(r'image.png', 0)skewed_image = cv2.imread(r'imageSkewed.png', 0)冲浪 = cv2.xfeatures2d.SURF_create(400)kp1, des1 = surf.detectAndCompute(orig_image, None)kp2, des2 = surf.detectAndCompute(skewed_image, 无)FLANN_INDEX_KDTREE = 0index_params = dict(算法=FLANN_INDEX_KDTREE，树=5)search_params = dict(检查=50)flann = cv2.FlannBasedMatcher(index_params, search_params)匹配 = flann.knnMatch(des1, des2, k=2)# 根据劳氏比率测试存储所有好的匹配.好=[]对于 m，n 匹配:如果 m.distance <0.7 * n.距离:好.追加(米)MIN_MATCH_COUNT = 10如果 len(good) >MIN_MATCH_COUNT 个: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, 掩码 = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)# 详见 https://ch.mathworks.com/help/images/examples/find-image-rotation-and-scale-using-automated-feature-matching.htmlss = M[0, 1]sc = M[0, 0]scaleRecovered = math.sqrt(ss * ss + sc * sc)thetaRecovered = math.atan2(ss, sc) * 180/math.piprint("计算的比例差:%.2f
计算的旋转差:%.2f" % (scaleRecovered, thetaRecovered))纠偏()别的:print("没有找到足够的匹配 - %d/%d" % (len(good), MIN_MATCH_COUNT))匹配掩码 = 无

I have an original page in digital form and several scanned versions of the same page. My goal is to deskew the scanned pages such that they match the original page as much as possible. I know that I could use the Probabilistic Hough Transform as described here for fixing the rotation but the scanned papers also differ in size as some people scaled the page to a different paper format. I think that the findHomography() function in OpenCV in combination with the keypoints from SIFT/SURF are exactly what I need to solve this problem. However, I just can't get my deskew() function to work.

Most of my code stems from the following two sources: http://www.learnopencv.com/homography-examples-using-opencv-python-c/ and 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()

解决方案

Turns out I was very close to solving my own problem. Here's the working version of my code:

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
Calculated rotation difference: %.2f" % (scaleRecovered, thetaRecovered))

    deskew()

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