pyimagesearch--imutils.py

# Import the necessary packages
import numpy as np
import cv2

def translate(image, x, y):
	# Define the translation matrix and perform the translation
	M = np.float32([[1, 0, x], [0, 1, y]])
	shifted = cv2.warpAffine(image, M, (image.shape[1], image.shape[0]))

	# Return the translated image
	return shifted

def rotate(image, angle, center = None, scale = 1.0):
	# Grab the dimensions of the image
	(h, w) = image.shape[:2]

	# If the center is None, initialize it as the center of
	# the image
	if center is None:
		center = (w / 2, h / 2)

	# Perform the rotation
	M = cv2.getRotationMatrix2D(center, angle, scale)
	rotated = cv2.warpAffine(image, M, (w, h))

	# Return the rotated image
	return rotated

def resize(image, width = None, height = None, inter = cv2.INTER_AREA):
	# initialize the dimensions of the image to be resized and
	# grab the image size
	dim = None
	(h, w) = image.shape[:2]

	# if both the width and height are None, then return the
	# original image
	if width is None and height is None:
		return image

	# check to see if the width is None
	if width is None:
		# calculate the ratio of the height and construct the
		# dimensions
		r = height / float(h)
		dim = (int(w * r), height)

	# otherwise, the height is None
	else:
		# calculate the ratio of the width and construct the
		# dimensions
		r = width / float(w)
		dim = (width, int(h * r))

	# resize the image
	resized = cv2.resize(image, dim, interpolation = inter)

	# return the resized image
	return resized

pyimagesearch--transform.py

# import the necessary packages
import numpy as np
import cv2

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[0] - bl[0]) ** 2))
	widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[0] - tl[0]) ** 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[1] - br[1]) ** 2) + ((tr[1] - br[1]) ** 2))
	heightB = np.sqrt(((tl[1] - bl[1]) ** 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

requirements.txt

numpy==1.8.2
scikit-image==0.10.1
scipy==0.14.0
six==1.7.3
wsgiref==0.1.2

scan.py

# USAGE
# python scan.py --image images/page.jpg 

# import the necessary packages
from pyimagesearch.transform import four_point_transform
from pyimagesearch import imutils
from skimage.filter import threshold_adaptive
import numpy as np
import argparse
import cv2

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required = True,
	help = "Path to the image to be scanned")
args = vars(ap.parse_args())

# load the image and compute the ratio of the old height
# to the new height, clone it, and resize it
image = cv2.imread(args["image"])
ratio = image.shape[0] / 500.0
orig = image.copy()
image = imutils.resize(image, height = 500)

# convert the image to grayscale, blur it, and find edges
# in the image
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()

# 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)
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()

# apply the four point transform to obtain a top-down
# view of the original image
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)

# convert the warped image to grayscale, then threshold it
# to give it that 'black and white' paper effect
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
warped = threshold_adaptive(warped, 250, offset = 10)
warped = warped.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)