def get_contour(self, rescaled_image):
"""
Returns a numpy array of shape (4, 2) containing the vertices of the four corners
of the document in the image. It considers the corners returned from get_corners()
and uses heuristics to choose the four corners that most likely represent
the corners of the document. If no corners were found, or the four corners represent
a quadrilateral that is too small or convex, it returns the original four corners.
"""
# these constants are carefully chosen
MORPH = 9
CANNY = 84
HOUGH = 25
IM_HEIGHT, IM_WIDTH, _ = rescaled_image.shape
# convert the image to grayscale and blur it slightly
gray = cv2.cvtColor(rescaled_image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (7, 7), 0)
# dilate helps to remove potential holes between edge segments
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (MORPH, MORPH))
dilated = cv2.dilate(gray, kernel)
# find edges and mark them in the output map using the Canny algorithm
edged = cv2.Canny(dilated, 0, CANNY)
test_corners = self.get_corners(edged)
approx_contours = []
if len(test_corners) >= 4:
quads = []
for quad in itertools.combinations(test_corners, 4):
points = np.array(quad)
points = transform.order_points(points)
points = np.array([[p] for p in points], dtype="int32")
quads.append(points)
# get top five quadrilaterals by area
quads = sorted(quads, key=cv2.contourArea, reverse=True)[:5]
# sort candidate quadrilaterals by their angle range, which helps remove outliers
quads = sorted(quads, key=self.angle_range)
approx = quads[0]
if self.is_valid_contour(approx, IM_WIDTH, IM_HEIGHT):
approx_contours.append(approx)
# for debugging: uncomment the code below to draw the corners and countour found
# by get_corners() and overlay it on the image
# cv2.drawContours(rescaled_image, [approx], -1, (20, 20, 255), 2)
# plt.scatter(*zip(*test_corners))
# plt.imshow(rescaled_image)
# plt.show()
# also attempt to find contours directly from the edged image, which occasionally
# produces better results
(_, cnts, hierarchy) = cv2.findContours(edged.copy(),
cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5]
# loop over the contours
for c in cnts:
# approximate the contour
approx = cv2.approxPolyDP(c, 80, True)
if self.is_valid_contour(approx, IM_WIDTH, IM_HEIGHT):
approx_contours.append(approx)
break
# If we did not find any valid contours, just use the whole image
if not approx_contours:
TOP_RIGHT = (IM_WIDTH, 0)
BOTTOM_RIGHT = (IM_WIDTH, IM_HEIGHT)
BOTTOM_LEFT = (0, IM_HEIGHT)
TOP_LEFT = (0, 0)
screenCnt = np.array([[TOP_RIGHT], [BOTTOM_RIGHT], [BOTTOM_LEFT],
[TOP_LEFT]])
else:
screenCnt = max(approx_contours, key=cv2.contourArea)
return screenCnt.reshape(4, 2)
def get_contour(self, image):
"""
Returns a numpy array of shape (4, 2) containing the vertices of the four corners
of the document in the image. It considers the corners returned from get_corners()
and uses heuristics to choose the four corners that most likely represent
the corners of the document. If no corners were found, or the four corners represent
a quadrilateral that is too small or convex, it returns the original four corners.
"""
# these constants are carefully chosen
MORPH = 9
CANNY = 84
HOUGH = 25
IM_HEIGHT, IM_WIDTH, _ = image.shape
# convert the image to grayscale and blur it slightly
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (7,7), 0)
# dilate helps to remove potential holes between edge segments
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(MORPH,MORPH))
dilated = cv2.dilate(gray, kernel)
# find edges and mark them in the output map using the Canny algorithm
edged = cv2.Canny(dilated, 0, CANNY)
test_corners = self.get_corners(edged)
approx_contours = []
if len(test_corners) >= 4:
quads = []
for quad in itertools.combinations(test_corners, 4):
points = np.array(quad)
points = transform.order_points(points)
points = np.array([[p] for p in points], dtype = "int32")
quads.append(points)
# get top five quadrilaterals by area
quads = sorted(quads, key=cv2.contourArea, reverse=True)[:5]
# sort candidate quadrilaterals by their angle range, which helps remove outliers
quads = sorted(quads, key=self.angle_range)
approx = quads[0]
if self.is_valid_contour(approx, IM_WIDTH, IM_HEIGHT):
approx_contours.append(approx)
# for debugging: uncomment the code below to draw the corners and countour found
# by get_corners() and overlay it on the image
# cv2.drawContours(rescaled_image, [approx], -1, (20, 20, 255), 2)
# plt.scatter(*zip(*test_corners))
# plt.imshow(rescaled_image)
# plt.show()
# also attempt to find contours directly from the edged image, which occasionally
# produces better results
(_, cnts, hierarchy) = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5]
# loop over the contours
for c in cnts:
# approximate the contour
approx = cv2.approxPolyDP(c, 80, True)
if self.is_valid_contour(approx, IM_WIDTH, IM_HEIGHT):
approx_contours.append(approx)
break
# If we did not find any valid contours, just use the whole image
if not approx_contours:
# TOP_RIGHT = (IM_WIDTH, 0)
# BOTTOM_RIGHT = (IM_WIDTH, IM_HEIGHT)
# BOTTOM_LEFT = (0, IM_HEIGHT)
# TOP_LEFT = (0, 0)
# screenCnt = np.array([[TOP_RIGHT], [BOTTOM_RIGHT], [BOTTOM_LEFT], [TOP_LEFT]])
# image = cv2.imread("79.png")
# print(type(image))
# orig=input()
# orig = image.copy()
(H, W) = image.shape[:2]
print(image.shape[:2])
height = image.shape[0]
width = image.shape[1]
# set the new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (3008,4032)
rW = W / float(newW)
rH = H / float(newH)
# resize the image and grab the new image dimensions
image = cv2.resize(image, (newW, newH))
(H, W) = image.shape[:2]
print(image.shape[:2])
# define the two output layer names for the EAST detector model that
# we are interested -- the first is the output probabilities and the
# second can be used to derive the bounding box coordinates of text
layerNames = [
"feature_fusion/Conv_7/Sigmoid",
"feature_fusion/concat_3"]
# load the pre-trained EAST text detector
print("[INFO] loading EAST text detector...")
net = cv2.dnn.readNet("E:/Users/NM/envs/cv/aidl/opencv-text-detection/opencv-text-detection/frozen_east_text_detection.pb")
# construct a blob from the image and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(image, 1.0, (W, H),
(123.68, 116.78, 103.94), swapRB=True, crop=False)
start = time.time()
net.setInput(blob)
(scores, geometry) = net.forward(layerNames)
end = time.time()
# show timing information on text prediction
print("[INFO] text detection took {:.6f} seconds".format(end - start))
# grab the number of rows and columns from the scores volume, then
# initialize our set of bounding box rectangles and corresponding
# confidence scores
(numRows, numCols) = scores.shape[2:4]
rects = []
confidences = []
# loop over the number of rows
for y in range(0, numRows):
# extract the scores (probabilities), followed by the geometrical
# data used to derive potential bounding box coordinates that
# surround text
scoresData = scores[0, 0, y]
xData0 = geometry[0, 0, y]
xData1 = geometry[0, 1, y]
xData2 = geometry[0, 2, y]
xData3 = geometry[0, 3, y]
anglesData = geometry[0, 4, y]
# loop over the number of columns
for x in range(0, numCols):
# if our score does not have sufficient probability, ignore it
if scoresData[x] < 0.5:
continue
# compute the offset factor as our resulting feature maps will
# be 4x smaller than the input image
(offsetX, offsetY) = (x * 4.0, y * 4.0)
# extract the rotation angle for the prediction and then
# compute the sin and cosine
angle = anglesData[x]
cos = np.cos(angle)
sin = np.sin(angle)
# use the geometry volume to derive the width and height of
# the bounding box
h = xData0[x] + xData2[x]
w = xData1[x] + xData3[x]
# compute both the starting and ending (x, y)-coordinates for
# the text prediction bounding box
endX = int(offsetX + (cos * xData1[x]) + (sin * xData2[x]))
endY = int(offsetY - (sin * xData1[x]) + (cos * xData2[x]))
startX = int(endX - w)
startY = int(endY - h)
# add the bounding box coordinates and probability score to
# our respective lists
rects.append((startX, startY, endX, endY))
confidences.append(scoresData[x])
# apply non-maxima suppression to suppress weak, overlapping bounding
# boxes
boxes = non_max_suppression(np.array(rects), probs=confidences)
list1=[]
list2=[]
list3=[]
list4=[]
# loop over the bounding boxes
for (startX, startY, endX, endY) in boxes:
# scale the bounding box coordinates based on the respective
# ratios
startX = int(startX * rW)
startY = int(startY * rH)
endX = int(endX * rW)
endY = int(endY * rH)
list1.append(startX)
list2.append(startY)
list3.append(endX)
list4.append(endY)
# draw the bounding box on the image
# cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2)
s1=min(list1)
print(s1)
s2=min(list2)
print(s2)
# print(list3)
e1=max(list3)
print(e1)
dic={}
e2=max(list4)
print(e2)
q1=(s1,s2)
q2=(e1,s2)
q3=(s1,e2)
q4=(e1,e2)
screenCnt = np.array([[q2], [q4], [q3], [q1]])
# dic={"topLeft":q1,"topRight":q2,"bottomLeft":q3,"bottomRight":q4}
# screenCnt = np.array([[TOP_RIGHT], [BOTTOM_RIGHT], [BOTTOM_LEFT], [TOP_LEFT]])
# return jsonify(dic)
else:
screenCnt = max(approx_contours, key=cv2.contourArea)
return screenCnt.reshape(4, 2)
def get_contour(self, rescaled_image):
MORPH = 9
CANNY = 84
HOUGH = 25
IM_HEIGHT, IM_WIDTH, _ = rescaled_image.shape
gray = cv2.cvtColor(rescaled_image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (7,7), 0)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(MORPH,MORPH))
dilated = cv2.dilate(gray, kernel)
edged = cv2.Canny(dilated, 0, CANNY)
test_corners = self.get_corners(edged)
approx_contours = []
if len(test_corners) >= 4:
quads = []
for quad in itertools.combinations(test_corners, 4):
points = np.array(quad)
points = transform.order_points(points)
points = np.array([[p] for p in points], dtype = "int32")
quads.append(points)
# get top five quadrilaterals by area
quads = sorted(quads, key=cv2.contourArea, reverse=True)[:5]
# sort candidate quadrilaterals by their angle range, which helps remove outliers
quads = sorted(quads, key=self.angle_range)
approx = quads[0]
if self.is_valid_contour(approx, IM_WIDTH, IM_HEIGHT):
approx_contours.append(approx)
# for debugging: uncomment the code below to draw the corners and countour found
# by get_corners() and overlay it on the image
# cv2.drawContours(rescaled_image, [approx], -1, (20, 20, 255), 2)
# plt.scatter(*zip(*test_corners))
# plt.imshow(rescaled_image)
# plt.show()
# also attempt to find contours directly from the edged image, which occasionally
# produces better results
(_, cnts, hierarchy) = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5]
# loop over the contours
for c in cnts:
# approximate the contour
approx = cv2.approxPolyDP(c, 80, True)
if self.is_valid_contour(approx, IM_WIDTH, IM_HEIGHT):
approx_contours.append(approx)
break
# If we did not find any valid contours, just use the whole image
if not approx_contours:
TOP_RIGHT = (IM_WIDTH, 0)
BOTTOM_RIGHT = (IM_WIDTH, IM_HEIGHT)
BOTTOM_LEFT = (0, IM_HEIGHT)
TOP_LEFT = (0, 0)
screenCnt = np.array([[TOP_RIGHT], [BOTTOM_RIGHT], [BOTTOM_LEFT], [TOP_LEFT]])
else:
screenCnt = max(approx_contours, key=cv2.contourArea)
return screenCnt.reshape(4, 2)
