Image Scanner project and Image lib

Author: Sarath Shekkizhar

.idea/ImageProcessingProjects.iml

@@ -0,0 +1,81 @@
+__author__ = 'Charlie'
+import os, sys, inspect
+import cv2
+import numpy as np
+import argparse
+
+# Info:
+# cmd_folder = os.path.dirname(os.path.abspath(__file__))
+# __file__ fails if script is called in different ways on Windows
+# __file__ fails if someone does os.chdir() before
+# sys.argv[0] also fails because it doesn't not always contains the path
+cmd_subfolder = os.path.realpath(os.path.abspath(os.path.join(os.path.split(inspect.getfile( inspect.currentframe() ))[0],"Image_Lib")))
+if cmd_subfolder not in sys.path:
+    sys.path.insert(0, cmd_subfolder)
+
+from image_transform import four_point_transform
+import image_utils as utils
+
+ap = argparse.ArgumentParser()
+ap.add_argument("-i", "--image", required = True, help = "Path to Image to be scanned")
+args = vars(ap.parse_args())
+
+image = cv2.imread(args["image"])
+ratio = image.shape[0]/500.0
+orig = image.copy()
+image = utils.image_resize(image, height = 500)
+
+gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+gray = cv2.GaussianBlur(gray, (5, 5), 0)
+# clahe = cv2.createCLAHE()
+# gray = clahe.apply(gray)
+edged = cv2.Canny(gray, 25, 75)
+
+# 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 = utils.adaptive_threshold(warped)
+warped = warped.astype("uint8")
+
+# show the original and scanned images
+print "STEP 3: Apply perspective transform"
+# cv2.imshow("Original", utils.image_resize(orig, height = 650))
+cv2.imshow("Scanned", utils.image_resize(warped, height = 650))
+cv2.waitKey(0)

.idea/misc.xml

@@ -0,0 +1 @@
+__author__ = 'Charlie'

.idea/workspace.xml

@@ -0,0 +1,63 @@
+__author__ = 'Charlie'
+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[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 warped

ImageScanner.py

@@ -0,0 +1,16 @@
+__author__ = 'Charlie'
+import cv2
+
+def image_resize(image, width = -1, height = -1):
+    shape = image.shape
+    if(width == -1):
+        if(height == -1):
+            return image
+        else:
+            return cv2.resize(image, (int(height * shape[1]/shape[0]), height))
+    elif (height == -1):
+        return cv2.resize(image, (width, int(width * shape[0]/shape[1])))
+
+
+def adaptive_threshold(image):
+    return cv2.adaptiveThreshold(image, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)