全能扫描王的实现（python版本）- 目标检测图像矫正

本方法适用于扫描文件，或者是形状规则（四个角上的点）的物体图片的校正。

0.导入必要的包

import numpy as np
import argparse
import cv2
import imutils

1.边缘检测

首先对图像进行处理。

# 设置读取图片的路径
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", default="scan.jpg",
	help = "Path to the image to be scanned") ## 这里修改为要扫描的图片的位置
args = vars(ap.parse_args())

# 加载原图 并对原图进行Resize
image = cv2.imread(args["image"])
ratio = image.shape[0] / 500.0
orig = image.copy()
image = imutils.resize(image, height = 500) #根据长宽比自动计算另外一边的尺寸进行resize

#根据处理找到边缘
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(gray, 75, 200)

# show the original image and the edge detected image
print("STEP 1: Edge Detection")
cv2.imshow("Image", image)
cv2.imshow("Edged", edged)
cv2.waitKey(0)
cv2.destroyAllWindows()

2. 找到轮廓

# find the contours in the edged image, keeping only the
# largest ones, and initialize the screen contour
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE) ## 找到轮廓
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5]

# loop over the contours
for c in cnts:
	# approximate the contour
	peri = cv2.arcLength(c, True)
	approx = cv2.approxPolyDP(c, 0.02 * peri, True)

	# if our approximated contour has four points, then we
	# can assume that we have found our screen
	if len(approx) == 4:
		screenCnt = approx
		break

# show the contour (outline) of the piece of paper
print("STEP 2: Find contours of paper")
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
cv2.imshow("Outline", image)
cv2.waitKey(0)
cv2.destroyAllWindows()

3. 图像校正

在本部分 首先要定义两个函数

def order_points(pts):
	# initialzie a list of coordinates that will be ordered
	# such that the first entry in the list is the top-left,
	# the second entry is the top-right, the third is the
	# bottom-right, and the fourth is the bottom-left
	rect = np.zeros((4, 2), dtype = "float32")

	# the top-left point will have the smallest sum, whereas
	# the bottom-right point will have the largest sum
	s = pts.sum(axis = 1)
	rect[0] = pts[np.argmin(s)]
	rect[2] = pts[np.argmax(s)]

	# now, compute the difference between the points, the
	# top-right point will have the smallest difference,
	# whereas the bottom-left will have the largest difference
	diff = np.diff(pts, axis = 1)
	rect[1] = pts[np.argmin(diff)]
	rect[3] = pts[np.argmax(diff)]

	# return the ordered coordinates
	return rect


def four_point_transform(image, pts):
	# obtain a consistent order of the points and unpack them
	# individually
	rect = order_points(pts)
	(tl, tr, br, bl) = rect

	# compute the width of the new image, which will be the
	# maximum distance between bottom-right and bottom-left
	# x-coordiates or the top-right and top-left x-coordinates
	widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
	widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
	maxWidth = max(int(widthA), int(widthB))

	# compute the height of the new image, which will be the
	# maximum distance between the top-right and bottom-right
	# y-coordinates or the top-left and bottom-left y-coordinates
	heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
	heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
	maxHeight = max(int(heightA), int(heightB))

	# now that we have the dimensions of the new image, construct
	# the set of destination points to obtain a "birds eye view",
	# (i.e. top-down view) of the image, again specifying points
	# in the top-left, top-right, bottom-right, and bottom-left
	# order
	dst = np.array([
		[0, 0],
		[maxWidth - 1, 0],
		[maxWidth - 1, maxHeight - 1],
		[0, maxHeight - 1]], dtype = "float32")

	# compute the perspective transform matrix and then apply it
	M = cv2.getPerspectiveTransform(rect, dst)
	warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

	# return the warped image
	return warped

然后调用函数就好了，如果需要进行扫描，二值化的话 把下面注释掉的代码放开就行，因为我只需要原图校正，所以不需要。（左图为原始图片，右侧为校正或者扫描后的硬盘图片。）

warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)

# convert the warped image to grayscale, then threshold it 
# 这里是二值化，也就是扫描成黑白的，可以把这部分放开注释，如果需要的话。
# to give it that 'black and white' paper effect
# warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
# T = threshold_local(warped, 11, offset = 10, method = "gaussian")
# warped = (warped > T).astype("uint8") * 255

# show the original and scanned images
print("STEP 3: Apply perspective transform")
cv2.imshow("Original", imutils.resize(orig, height = 650))
cv2.imshow("Scanned", imutils.resize(warped, height = 650))
cv2.waitKey(0)