diff --git a/image_align_scan.py b/image_align_scan.py new file mode 100644 index 0000000..1b4e6dc --- /dev/null +++ b/image_align_scan.py @@ -0,0 +1,103 @@ +from skimage.filters import threshold_local +import numpy as np +import argparse +import cv2 +import imutils +import os + + +current_path=os.getcwd() + +ap = argparse.ArgumentParser() +ap.add_argument("-i", "--image", required = True) +args = vars(ap.parse_args()) + + + +def order_points(pts): + rect = np.zeros((4, 2), dtype = "float32") + s = pts.sum(axis = 1) + rect[0] = pts[np.argmin(s)] + rect[2] = pts[np.argmax(s)] + diff = np.diff(pts, axis = 1) + rect[1] = pts[np.argmin(diff)] + rect[3] = pts[np.argmax(diff)] + return rect + + + +def four_point_transform(image, pts): + rect = order_points(pts) + (tl, tr, br, bl) = rect + 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)) + 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)) + dst = np.array([ + [0, 0], + [maxWidth - 1, 0], + [maxWidth - 1, maxHeight - 1], + [0, maxHeight - 1]], dtype = "float32") + M = cv2.getPerspectiveTransform(rect, dst) + warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight)) + return warped + + + + + +image = cv2.imread(args["image"]) +ratio = image.shape[0] / 500.0 +orig = image.copy() +image = imutils.resize(image, height = 500) +gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +gray = cv2.GaussianBlur(gray, (5, 5), 0) +edged = cv2.Canny(gray, 75, 200) +cv2.imshow("Image", image) +cv2.imshow("Edged", edged) +print("STEP 1: Edge Detection") +cv2.waitKey(0) +cv2.destroyAllWindows() + + + + + +cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE) +cnts = imutils.grab_contours(cnts) +cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5] +for c in cnts: + peri = cv2.arcLength(c, True) + approx = cv2.approxPolyDP(c, 0.02 * peri, True) + if len(approx) == 4: + screenCnt = approx + break +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() + + + + +warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio) +warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY) + +# warped = cv2.adaptiveThreshold(warped, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 251, 11) + + + +T = threshold_local(warped, 11, offset = 10, method = "gaussian") +warped = (warped > T).astype("uint8") * 255 + +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) + + + +cv2.imwrite(current_path+'/Scanned.png',imutils.resize(warped, height = 650)) diff --git a/img3.jpg b/img3.jpg new file mode 100644 index 0000000..702b299 Binary files /dev/null and b/img3.jpg differ