def cropCircle(img):
'''
there many imaged taken thresholded, which means many images is
present as a circle with black surrounded. This function is to
find the largest inscribed rectangle to the thresholed image and
then crop the image to the rectangle.
input: img - the cv2 module
return: img_crop, rectangle, tile_size
'''
if(img.shape[0] > img.shape[1]):
tile_size = (int(img.shape[1]*256/img.shape[0]),256)
else:
tile_size = (256, int(img.shape[0]*256/img.shape[1]))
img = cv2.resize(img, dsize=tile_size)
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY);
_, thresh = cv2.threshold(gray, 10, 255, cv2.THRESH_BINARY)
_, contours, _ = cv2.findContours(thresh.copy(),cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
main_contour = sorted(contours, key = cv2.contourArea, reverse = True)[0]
ff = np.zeros((gray.shape[0],gray.shape[1]), 'uint8')
cv2.drawContours(ff, main_contour, -1, 1, 15)
ff_mask = np.zeros((gray.shape[0]+2,gray.shape[1]+2), 'uint8')
cv2.floodFill(ff, ff_mask, (int(gray.shape[1]/2), int(gray.shape[0]/2)), 1)
rect = maxRect(ff)
rectangle = [min(rect[0],rect[2]), max(rect[0],rect[2]), min(rect[1],rect[3]), max(rect[1],rect[3])]
img_crop = img[rectangle[0]:rectangle[1], rectangle[2]:rectangle[3]]
cv2.rectangle(ff,(min(rect[1],rect[3]),min(rect[0],rect[2])),(max(rect[1],rect[3]),max(rect[0],rect[2])),3,2)
return [img_crop, rectangle, tile_size]
python类RETR_TREE的实例源码
def cropCircle(img):
'''
there many imaged taken thresholded, which means many images is
present as a circle with black surrounded. This function is to
find the largest inscribed rectangle to the thresholed image and
then crop the image to the rectangle.
input: img - the cv2 module
return: img_crop, rectangle, tile_size
'''
if(img.shape[0] > img.shape[1]):
tile_size = (int(img.shape[1]*256/img.shape[0]),256)
else:
tile_size = (256, int(img.shape[0]*256/img.shape[1]))
img = cv2.resize(img, dsize=tile_size)
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY);
_, thresh = cv2.threshold(gray, 10, 255, cv2.THRESH_BINARY)
_, contours, _ = cv2.findContours(thresh.copy(),cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
main_contour = sorted(contours, key = cv2.contourArea, reverse = True)[0]
ff = np.zeros((gray.shape[0],gray.shape[1]), 'uint8')
cv2.drawContours(ff, main_contour, -1, 1, 15)
ff_mask = np.zeros((gray.shape[0]+2,gray.shape[1]+2), 'uint8')
cv2.floodFill(ff, ff_mask, (int(gray.shape[1]/2), int(gray.shape[0]/2)), 1)
rect = maxRect(ff)
rectangle = [min(rect[0],rect[2]), max(rect[0],rect[2]), min(rect[1],rect[3]), max(rect[1],rect[3])]
img_crop = img[rectangle[0]:rectangle[1], rectangle[2]:rectangle[3]]
cv2.rectangle(ff,(min(rect[1],rect[3]),min(rect[0],rect[2])),(max(rect[1],rect[3]),max(rect[0],rect[2])),3,2)
return [img_crop, rectangle, tile_size]
def extract_black_contours(img):
"""
Extract contours for black objects on a white background.
Args:
img (np.ndarray): the (black and white?) image
Returns:
list[np.ndarray]: the contours
"""
img_inverted = 255 - img
_, contours, _ = cv2.findContours(img_inverted, mode=cv2.RETR_TREE, method=cv2.CHAIN_APPROX_SIMPLE)
return contours
# TODO: A ContourGroups class would make this cleaner
digital_display_ocr.py 文件源码
项目：digital-display-character-rec
作者: upupnaway
项目源码
文件源码
阅读 22
收藏 0
点赞 0
评论 0
def find_display_contour(edge_img_arr):
display_contour = None
edge_copy = edge_img_arr.copy()
contours,hierarchy = cv2.findContours(edge_copy, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
top_cntrs = sorted(contours, key = cv2.contourArea, reverse = True)[:10]
for cntr in top_cntrs:
peri = cv2.arcLength(cntr,True)
approx = cv2.approxPolyDP(cntr, 0.02 * peri, True)
if len(approx) == 4:
display_contour = approx
break
return display_contour
def FindField(self):
#Feld: Hue zwischen 60 und 100
LowerGreen = np.array([40,0,0])
UpperGreen = np.array([90,255,150])
mask = cv2.inRange(self.ImgHSV,LowerGreen,UpperGreen)
# plt.figure()
# plt.imshow(mask,cmap='gray')
mask = self.SmoothFieldMask(mask)
# plt.figure()
# plt.imshow(mask.copy(),cmap='gray')
im2, contours, hierarchy = cv2.findContours(mask.copy(),cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
if(len(contours) <= 0):
return
contours_sorted = sorted(contours, key = cv2.contourArea, reverse=True)[:10]
peri = cv2.arcLength(contours_sorted[0],True)
approx = cv2.approxPolyDP(contours_sorted[0], 0.02*peri, True)
if(len(approx) >-1):#== 4):
self.FieldContours = approx
cv2.rectangle(mask,(((self.FieldContours[0])[0])[0],((self.FieldContours[0])[0])[1]),(((self.FieldContours[2])[0])[0],((self.FieldContours[2])[0])[1]),(128,128,128),3)
# plt.imshow(mask, cmap="gray")
# plt.show()
def create_bounding_box(img_path, outfile_name, random_noise = True):
img = cv2.imread(img_path)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, binary_img = cv2.threshold(img_gray,127,255,cv2.THRESH_BINARY)
# show the binary_image
# plt.subplot(1,1,1), plt.imshow(binary_img,'gray')
# plt.show()
image_cnt, contours, _ = cv2.findContours(binary_img,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])
if (random_noise == True):
w_org = w
h_org = h
x = int(np.random.normal(x, w_org * 0.15, 1))
y = int(np.random.normal(y, h_org * 0.15, 1))
w = int(np.random.normal(w, w_org * 0.15, 1))
h = int(np.random.normal(h, h_org * 0.15, 1))
height, width, channels = img.shape
out_img = np.zeros((height,width,1), np.uint8)
cv2.rectangle(out_img,(x,y),(x+w,y+h),(255,0,0),-1)
cv2.imwrite(outfile_name, out_img)
def movement(mat_1,mat_2):
mat_1_gray = cv2.cvtColor(mat_1.copy(),cv2.COLOR_BGR2GRAY)
mat_1_gray = cv2.blur(mat_1_gray,(blur1,blur1))
_,mat_1_gray = cv2.threshold(mat_1_gray,100,255,0)
mat_2_gray = cv2.cvtColor(mat_2.copy(),cv2.COLOR_BGR2GRAY)
mat_2_gray = cv2.blur(mat_2_gray,(blur1,blur1))
_,mat_2_gray = cv2.threshold(mat_2_gray,100,255,0)
mat_2_gray = cv2.bitwise_xor(mat_1_gray,mat_2_gray)
mat_2_gray = cv2.blur(mat_2_gray,(blur2,blur2))
_,mat_2_gray = cv2.threshold(mat_2_gray,70,255,0)
mat_2_gray = cv2.erode(mat_2_gray,np.ones((erodeval,erodeval)))
mat_2_gray = cv2.dilate(mat_2_gray,np.ones((4,4)))
_, contours,__ = cv2.findContours(mat_2_gray,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
if len(contours) > 0:return True #If there were any movements
return False #if not
#Pedestrian Recognition Thread
def Q2():
cap = cv2.VideoCapture(0)
while(cap.isOpened() ):
ret = cap.set(3,320)
ret = cap.set(4,240)
ret, frame = cap.read()
if ret==True:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
x,thresh = cv2.threshold(gray,137,255,1)
contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(frame, contours,-1, (0,255,0), 3)
cv2.imshow('Image with contours',frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
break
cap.release()
cv2.destroyAllWindows()
def sizeFiltering(contours):
#this function filters out the smaller retroreflector (as well as any noise) by size
#_, contours, _ = cv2.findContours(img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
"""blank_image = np.zeros((img.shape[0],img.shape[1],3), np.uint8)
cv2.drawContours(blank_image, contours, -1, (255, 255, 255))
cv2.imshow("imagia", blank_image)
cv2.waitKey()"""
if len(contours) == 0:
print "errorrrrr"
return 0
big = contours[0]
for c in contours:
if type(c) and type(big) == np.ndarray:
if cv2.contourArea(c) > cv2.contourArea(big):
big = c
else:
print type(c) and type(big)
return 0
"""blank_image = np.zeros((img.shape[0],img.shape[1],3), np.uint8)
cv2.drawContours(blank_image, big, -1, (255, 255, 255))
cv2.imshow("imagia", blank_image)
cv2.waitKey()"""
"""blank_image = np.zeros((img.shape[0],img.shape[1],3), np.uint8)
cv2.drawContours(blank_image, big, -1, (255, 255, 255))"""
x,y,w,h = cv2.boundingRect(big)
"""cv2.rectangle(blank_image, (x,y), (x+w, y+h), (255,255,255))
cv2.imshow("rect", blank_image)
cv2.waitKey()"""
return big
def shapeFiltering(img):
contours = cv2.findContours(img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)[0]
if len(contours) == 0:
return "yoopsie"
#else:
#print contours
"""blank_image = np.zeros((img.shape[0],img.shape[1],3), np.uint8)
cv2.drawContours(blank_image, contours, -1, (255, 255, 255))
cv2.imshow("imagiae", blank_image)
cv2.waitKey()"""
good_shape = []
for c in contours:
x,y,w,h = cv2.boundingRect(c)
"""rect = cv2.minAreaRect(contour)
box = cv2.boxPoints(rect)
box = np.int0(box)
w = """
#if h == 0:
# continue
ratio = w / h
ratio_grade = ratio / (TMw / TMh)
if 0.2 < ratio_grade < 1.8:
good_shape.append(c)
"""blank_image = np.zeros((img.shape[0],img.shape[1],3), np.uint8)
cv2.drawContours(blank_image, good_shape, -1, (255, 255, 255))
cv2.imshow("imagia", blank_image)
cv2.waitKey()"""
return good_shape
def track(self, com, size=(250, 250, 250), dsize=(128, 128), doHandSize=True):
"""
Detect the hand as closest object to camera
:param size: bounding box size
:return: center of mass of hand
"""
# calculate boundaries
xstart, xend, ystart, yend, zstart, zend = self.comToBounds(com, size)
# crop patch from source
cropped = self.getCrop(self.dpt, xstart, xend, ystart, yend, zstart, zend)
# predict movement of CoM
if self.refineNet is not None and self.importer is not None:
rz = self.resizeCrop(cropped, dsize)
newCom3D = self.refineCoM(rz, size, com) + self.importer.jointImgTo3D(com)
com = self.importer.joint3DToImg(newCom3D)
if numpy.allclose(com, 0.):
com[2] = cropped[cropped.shape[0]//2, cropped.shape[1]//2]
else:
raise RuntimeError("Need refineNet for this")
if doHandSize is True:
# refined contour for size estimation
zstart = com[2] - size[2] / 2.
zend = com[2] + size[2] / 2.
part_ref = self.dpt.copy()
part_ref[part_ref < zstart] = 0
part_ref[part_ref > zend] = 0
part_ref[part_ref != 0] = 10 # set to something
ret, thresh_ref = cv2.threshold(part_ref, 1, 255, cv2.THRESH_BINARY)
contours_ref, _ = cv2.findContours(thresh_ref.astype(dtype=numpy.uint8), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# find the largest contour
areas = [cv2.contourArea(cc) for cc in contours_ref]
c_max = numpy.argmax(areas)
# final result
return com, self.estimateHandsize(contours_ref[c_max], com, size)
else:
return com, size
def find_concetric_circles(gray_img,min_ring_count=3, visual_debug=False):
# get threshold image used to get crisp-clean edges using blur to remove small features
edges = cv2.adaptiveThreshold(cv2.blur(gray_img,(3,3)), 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 5, 11)
_, contours, hierarchy = cv2.findContours(edges,
mode=cv2.RETR_TREE,
method=cv2.CHAIN_APPROX_NONE,offset=(0,0)) #TC89_KCOS
if visual_debug is not False:
cv2.drawContours(visual_debug,contours,-1,(200,0,0))
if contours is None or hierarchy is None:
return []
clusters = get_nested_clusters(contours,hierarchy[0],min_nested_count=min_ring_count)
concentric_cirlce_clusters = []
#speed up code by caching computed ellipses
ellipses = {}
# for each cluster fit ellipses and cull members that dont have good ellipse fit
for cluster in clusters:
if visual_debug is not False:
cv2.drawContours(visual_debug, [contours[i] for i in cluster],-1, (0,0,255))
candidate_ellipses = []
for i in cluster:
c = contours[i]
if len(c)>5:
if not i in ellipses:
e = cv2.fitEllipse(c)
fit = max(dist_pts_ellipse(e,c))
ellipses[i] = e,fit
else:
e,fit = ellipses[i]
a,b = e[1][0]/2.,e[1][1]/2.
if fit<max(2,max(e[1])/20):
candidate_ellipses.append(e)
if visual_debug is not False:
cv2.ellipse(visual_debug, e, (0,255,0),1)
if candidate_ellipses:
cluster_center = np.mean(np.array([e[0] for e in candidate_ellipses]),axis=0)
candidate_ellipses = [e for e in candidate_ellipses if np.linalg.norm(e[0]-cluster_center)<max(3,min(e[1])/20) ]
if len(candidate_ellipses) >= min_ring_count:
concentric_cirlce_clusters.append(candidate_ellipses)
if visual_debug is not False:
cv2.ellipse(visual_debug, candidate_ellipses[-1], (0,255,255),4)
#return clusters sorted by size of outmost cirlce biggest first.
return sorted(concentric_cirlce_clusters,key=lambda e:-max(e[-1][1]))
def single_finger_check(self, cnt):
# use single finger image to check current fame has single finger
grey_fin1 = cv2.cvtColor(self.fin1, cv2.COLOR_BGR2GRAY)
_, thresh_fin1 = cv2.threshold(grey_fin1, 127, 255, 0)
contour_fin1, hierarchy = cv2.findContours(thresh_fin1.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt1 = contour_fin1[0]
ret1 = cv2.matchShapes(cnt, cnt1, 1, 0)
grey_fin2 = cv2.cvtColor(self.fin2, cv2.COLOR_BGR2GRAY)
_, thresh_fin2 = cv2.threshold(grey_fin2, 127, 255, 0)
contour_fin2, hierarchy = cv2.findContours(thresh_fin2.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt2 = contour_fin2[0]
ret2 = cv2.matchShapes(cnt, cnt2, 1, 0)
grey_fin3 = cv2.cvtColor(self.fin3, cv2.COLOR_BGR2GRAY)
_, thresh_fin3 = cv2.threshold(grey_fin3, 127, 255, 0)
contour_fin3, hierarchy = cv2.findContours(thresh_fin3.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt3 = contour_fin3[0]
ret3 = cv2.matchShapes(cnt, cnt3, 1, 0)
reta = (ret1 + ret2 + ret3)/3
if reta <= 0.3:
return 5 # set as one-finger module
else:
return 0 # not detect, still 0
# Use PyAutoGUI to control mouse event
def find(self, mode):
self.mode = mode
if mode == 1:
self.modeDesc = 'Run gaussianBlur(), then cannyThresholding'
self.gaussianBlur()
self.cannyThresholding()
elif mode == 2:
# Check Gimp Hints
self.gimpMarkup()
#self.cannyThresholding()
self.modeDesc = 'Run gimpMarkup'
elif mode == 3:
# Massively mask red as a precursor phase
self.gaussianBlur()
self.colourMapping()
self.solidRedFilter()
#self.cannyThresholding()
self.modeDesc = 'Run gaussianBlur(), colourMapping(), solidRedFilter(), #cannyThresholding'
elif mode == 4:
self.modeDesc = 'Run gaussianBlur(), then cannyThresholding with RETR_EXTERNAL contour removal mode'
self.gaussianBlur()
self.cannyThresholding(cv2.RETR_EXTERNAL)
elif mode == 5:
self.modeDesc = 'Run gaussianBlur(), then cannyThresholding with RETR_TREE contour removal mode'
self.gaussianBlur()
self.cannyThresholding(cv2.RETR_TREE)
# Apply Heuristics to filter out false
self.squares = filterContoursRemove(self.img, self.squares)
return self.squares
def binaryContoursNestingFilterHeuristic(img, cnts, *args, **kwargs):
'''
Concept : Use the found contours, with binary drawn contours to extract hierarchy and hence filter on nesting.
Critique : WIP
'''
# Set the image to black (0):
img[:,:] = (0,0,0)
# Draw all of the contours on the image in white
contours = [c.contour for c in cnts]
cv2.drawContours( img, contours, -1, (255, 255, 255), 1 )
iv = ImageViewer(img)
iv.windowShow()
# Now extract any channel
gray = cv2.split(img)[0]
iv = ImageViewer(gray)
iv.windowShow()
retval, bin = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY)
iv = ImageViewer(bin)
iv.windowShow()
# Now find the contours again, but this time we care about hierarchy (hence _TREE) - we get back next, previous, first_child, parent
bin, contours, hierarchy = cv2.findContours(bin, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
iv = ImageViewer(bin)
iv.windowShow()
# Alternative flags : only take the external contours
bin, contours, hierarchy = cv2.findContours(bin, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
iv = ImageViewer(bin)
iv.windowShow()
return cnts
def usage():
print('''
piwall.py
--vssdemo|-v rotating : iterate the VideoSquareSearch over rotating video, and output located data in piwall-search-mono.avi
--vssdemo|-v album : iterate the VideoSquareSearch over sequence of images, and output located data in album.avi
--sfv3mode|-s [mode 1-3] : run the SquareLocatorV3 algorithm : set the mode 1-3 < default image 2x2-red-1.jpg >
: 1 => call gaussianBlur(); cannyThresholding()
: 2 => call gimpMarkup()
: 3 => call gaussianBlur(); colourMapping(); solidRedFilter(); [#cannyThresholding]
: 4 => as 1, but with cv2.RETR_EXTERNAL as contour_retrieval_mode
: 5 => as 1, but with cv2.RETR_TREE as contour_retrieval_mode, then filter only outermost contours
: 6 => new model which takes a series of images which have transitions that identify the monitors.
--sfv3img|-i [image path]: run the SquareFinderV3 algorithm : set the input image < default mode 1>
--sfv4glob|-g [image glob pattern] : set the series of input images to be pattern-[%03d].jpg
''')
def find_contours(image):
#return cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE);
#return cv2.findContours(image, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE);
return cv2.findContours(image, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE);
def find_bbox(mask_binary, margin_factor=None):
ret, thresh = cv2.threshold(mask_binary, 127, 255, 0)
_, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# Find the index of the largest contour
areas = [cv2.contourArea(c) for c in contours]
if len(areas) == 0:
return (0, 0, mask_binary.shape[0], mask_binary.shape[1], False)
else:
max_index = np.argmax(areas)
cnt = contours[max_index]
x, y, w, h = cv2.boundingRect(cnt)
if margin_factor != None and margin_factor > 0:
wm = w * margin_factor
hm = h * margin_factor
x -= wm
y -= hm
w += 2 * wm
h += 2 * hm
x = max(0, x)
y = max(0, y)
X = min(x + w, mask_binary.shape[1])
Y = min(y + h, mask_binary.shape[0])
w = X - x
h = Y - y
return (int(x), int(y), int(w), int(h), True)
def get_operator(path, url=False, expand=False):
if url:
req = requests.get(path)
arr = np.asarray(bytearray(req.content), dtype=np.uint8)
shape = cv2.resize(cv2.imdecode(arr, -1), (69, 69))
else:
shape = cv2.resize(cv2.imread('shape.png'), (69, 69))
shape_gray = cv2.cvtColor(shape, cv2.COLOR_BGR2GRAY)
_, shape_binary = cv2.threshold(shape_gray, 127, 255, cv2.THRESH_BINARY)
_, contours, hierarchy = cv2.findContours(shape_binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
contour = contours[0]
operator = np.zeros((69, 69))
for point in contour:
operator[point[0][0]][point[0][1]] = 1
if expand:
if point[0][0] > 0:
operator[point[0][0] - 1][point[0][1]] = 1
if point[0][0] < 68:
operator[point[0][0] + 1][point[0][1]] = 1
if point[0][1] > 0:
operator[point[0][0]][point[0][1] - 1] = 1
if point[0][1] < 68:
operator[point[0][0]][point[0][1] + 1] = 1
return operator
