def equalize_hist(img):
if len(img.shape) > 2 and img.shape[2] > 1:
img_yuv = cv2.cvtColor(img, cv2.COLOR_BGR2YUV)
img_yuv[:, :, 0] = cv2.equalizeHist(img_yuv[:, :, 0])
return cv2.cvtColor(img_yuv, cv2.COLOR_YUV2BGR)
else:
return cv2.equalizeHist(img)
def hisEqulColor(img):
if len(img.shape) == 2:
return hisEqul(img)
ycrcb = cv2.cvtColor(img, cv2.COLOR_BGR2YCR_CB)
channels = cv2.split(ycrcb)
cv2.equalizeHist(channels[0], channels[0])
cv2.merge(channels, ycrcb)
cv2.cvtColor(ycrcb, cv2.COLOR_YCR_CB2BGR, img)
return img
def base():
if request.method == 'GET':
return "<h1>Crop AI</h1>"
if request.method == 'POST':
if 'InputImg' not in request.files:
print("No file part")
return redirect(request.url)
file = request.files['InputImg']
if file.filename == '':
print('No selected file')
return redirect(request.url)
if file and allowed_file(file.filename):
filestr = request.files['InputImg'].read()
img = cv2.imdecode(np.fromstring(filestr, np.uint8),
cv2.IMREAD_COLOR)
img = cv2.resize(img, (96, 96), interpolation=cv2.INTER_AREA)
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# find the green color
mask_green = cv2.inRange(hsv, (36, 0, 0), (86, 255, 255))
# find the brown color
mask_brown = cv2.inRange(hsv, (8, 60, 20), (145, 255, 255))
# find the yellow color in the leaf
mask_yellow = cv2.inRange(hsv, (5, 42, 143), (145, 255, 255))
# find the black color in the leaf
mask_black = cv2.inRange(hsv, (100, 100, 100), (127, 127, 127))
# find any of the four colors(green or brown or yellow or black) in the image
mask = cv2.bitwise_or(mask_green, mask_brown)
mask = cv2.bitwise_or(mask, mask_yellow)
mask = cv2.bitwise_or(mask, mask_black)
# Bitwise-AND mask and original image
res = cv2.bitwise_and(img, img, mask=mask)
# Gaussian blur with 3x3 kernel
blur_img = cv2.GaussianBlur(res, (3, 3), 0)
# Histogram equalization
B, G, R = cv2.split(blur_img)
output_R = cv2.equalizeHist(R)
output_G = cv2.equalizeHist(G)
output_B = cv2.equalizeHist(B)
img = cv2.merge((output_R, output_G, output_B))
img = img / 255
img_array = np.expand_dims(img, axis=0)
output = label_dictionary[model.predict(img_array)[0].argmax()]
return output
def adapt_hist_equilization(img):
#img = cv2.imread("test_001.jpg")
R, G, B = cv2.split(img)
output1_R = cv2.equalizeHist(R)
output1_G = cv2.equalizeHist(G)
output1_B = cv2.equalizeHist(B)
equ = cv2.merge((output1_R, output1_G, output1_B))
res = np.hstack((img, equ)) #stacking images side-by-side
return res
def preprocess_ir_image(self, image: np.array) -> np.array:
if self.preprocessing_method == self.NONE:
channels = [image] * 3
elif self.preprocessing_method == self.INVERT_EQUALIZE:
channels = [cv2.equalizeHist(np.invert(image))] * 3
elif self.preprocessing_method == self.THREE_CHANNEL_NONE_INVERT_EQUALIZE:
channels = [image, np.invert(image), cv2.equalizeHist(image)]
elif self.preprocessing_method == self.INVERT:
channels = [np.invert(image)] * 3
elif self.preprocessing_method == self.EQUALIZE:
channels = [cv2.equalizeHist(image)] * 3
else:
raise ValueError("Unknown preprocessing type")
return np.stack(channels, axis=2)
def detectAndDisplay(frame):
frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frame_gray = cv2.equalizeHist(frame_gray)
# Detectar faces
# Divide a imagem em diversos retângulos e retorna uma lista com eles
faces = face_cascade.detectMultiScale(frame_gray)
for (x, y, w, h) in faces:
center = (x + w // 2, y + h // 2)
# Elipses rosas
frame = cv2.ellipse(frame, center, (w // 2, h // 2), 0, 0, 360,
(255, 0, 255), 4)
faceROI = frame_gray[y:y + h, x:x + w]
# Em cada face, detectar olhos
eyes = eyes_cascade.detectMultiScale(faceROI)
for (x2, y2, w2, h2) in eyes:
eye_center = (x + x2 + w2 // 2, y + y2 + h2 // 2)
radius = int(round((w2 + h2) * 0.25))
# Circulos azuis
frame = cv2.circle(frame, eye_center, radius, (255, 0, 0), 4)
# Frame invertido horizontalmente por questão de estética =)
frame = cv2.flip(frame, 1)
cv2.imshow('Deteccao de Face e Olho', frame)
return frame
def detect(filename, s, cascade_file = "../lbpcascade_animeface.xml"):
if not os.path.isfile(cascade_file):
raise RuntimeError("%s: not found" % cascade_file)
try:
print('trying image {}'.format(s))
cascade = cv2.CascadeClassifier(cascade_file)
image = cv2.imread(filename, cv2.IMREAD_COLOR)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.equalizeHist(gray)
faces = cascade.detectMultiScale(gray,
# detector options
scaleFactor = 1.1,
minNeighbors = 5,
minSize = (24, 24))
for (x, y, w, h) in faces:
#cv2.rectangle(image, (x-w//4, y-w//4), (x + 5*w//4, y + 5*h//4), (0, 0, 255), 2)
out = image[y-21:y+107,x-21:x+107]
#out = image[y-42:y+214,x-42:x+214]
#cv2.imshow("AnimeFaceDetect", image)
#cv2.waitKey(0)
cv2.imwrite("cropped/{}.jpg".format(s), out)
print('success!')
except:
print('one pic error!')
def demo_thersholding(img,
threshold=None,
show=True,
thresh_type=cv2.THRESH_BINARY_INV):
plt.figure(654)
hist, bins = np.histogram(img.ravel(), 256, [0, 256])
threshold = threshold if threshold is not None else bins[hist.argmax()]
# threshold = threshold if threshold is not None else np.median(img)
# aimg = cv2.cvtColor(img/255, cv2.COLOR_BGR2GRAY) # or convert
equ = cv2.equalizeHist(img.astype(np.uint8))
threshold, equ_threshed = cv2.threshold(equ, threshold, equ.max(),
thresh_type)
if show:
# Show histogram
cdf = hist.cumsum()
cdf_normalized = cdf * hist.max() / cdf.max()
plt.plot(cdf_normalized, color='b')
plt.hist(img.flatten(), 256, [0, 256], color='r')
plt.xlim([0, 256])
plt.legend(('cdf', 'histogram'), loc='upper left')
plt.show()
# Compare images
res = np.hstack(
(img, equ.astype(np.float))) # stacking images side-by-side
threshold, ret = cv2.threshold(res, threshold, res.max(), thresh_type)
ret = ret / 255.
cv2.imshow('try...', ret)
cv2.waitKey(0)
return equ_threshed
def main(img_path):
"""Using OpenCV’s histogram equalization method equalizeHist, write a
program that improves the contrast of an input image. Visually inspect the
output image and comment how histogram equalization changes its contrast.
Compute the histograms of the input and equalized images and comment how the
histogram has been stretched out more widely and uniformly.
:param img: the path to an image
:type img: str
"""
# load in the image
image = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE)
# show the image
utils.show('original', image)
# look at the histogram of the original image
utils.show_hist_gray(image)
# equalise the histogram
equalised = cv2.equalizeHist(image)
# show the new image
utils.show('equalised', equalised)
# look at the histogram now
utils.show_hist_gray(equalised)
def _preprocess(self, warped_img):
'''
Preprocess the warped and rotated image.
@warped_img:
np.array, it should be the output of self._polar_warp_and_rotate().
@return:
(s_mask, output_img), saturation mask and image after preprocessing.
'''
warped_img = cv.GaussianBlur(warped_img, (3, 3), 1.5)
hsv = cv.cvtColor(warped_img, cv.COLOR_BGR2HSV)
warped_img = cv.cvtColor(warped_img, cv.COLOR_BGR2GRAY)
warped_img = cv.equalizeHist(warped_img) # Enhance contrast
_, s, _ = cv.split(hsv)
_, s = cv.threshold(s, 0, 255, cv.THRESH_OTSU)
s = cv.morphologyEx(s, cv.MORPH_ERODE, np.ones((5, 5)))
_, contours, _ = cv.findContours(s, cv.RETR_TREE,
cv.CHAIN_APPROX_SIMPLE)
contours = sorted(contours, key=lambda ctr: cv.contourArea(ctr)
) # Sort to choose the largest area
mask = cv.drawContours(np.zeros((warped_img.shape), np.uint8),
contours,
len(contours) - 1, (255, 255, 255),
thickness=1)
box = cv.boundingRect(get_points(mask)) # Largest area box-bouding
mask = cv.rectangle(mask, (box[0], box[1]),
(box[0] + box[2], box[1] + box[3]),
(255, 255, 255),
cv.FILLED) # Fill the area that is to be removed
mask = cv.bitwise_not(mask) # Ensure tooth existing area
return mask, warped_img
def equalize(img: np.ndarray) -> np.ndarray:
"""
Args:
img: image as numpy array
Returns:
image
"""
if is_colored(img):
equ_b = cv2.equalizeHist(get_color(img, "b"))
equ_g = cv2.equalizeHist(get_color(img, "g"))
equ_r = cv2.equalizeHist(get_color(img, "r"))
return cv2.merge((equ_b, equ_g, equ_r))
else:
return cv2.equalizeHist(img)
def select_image():
# grab a reference to the image panels
global panelA, panelB
# open a file chooser dialog and allow the user to select an input
# image
path = filedialog.askopenfilename()
path_out = '/home/anibe/Desktop/augustine/'
img_path_in = path
img_path_out = path_out + 'filtered.png'
# ensure a file path was selected
if len(path) > 0:
img = cv2.imread(img_path_in)[:, :, 0]
homo_filter = HomomorphicFilter(a=0.75, b=1.25)
img_filtered = homo_filter.filter(I=img, filter_params=[30, 2])
cv2.imwrite(img_path_out, img_filtered)
#HISTOGRAM EQUALIZATION APPLIED HERE
cv2.equalizeHist(img)
# convert the images to PIL format...
image = Image.fromarray(img)
edged = Image.fromarray(img_filtered)
# ...and then to ImageTk format
image = ImageTk.PhotoImage(image)
edged = ImageTk.PhotoImage(edged)
# if the panels are None, initialize them
if panelA is None or panelB is None:
# the first panel will store our original image
panelA = Label(image=image)
panelA.image = image
panelA.pack(side="left", padx=10, pady=10)
# while the second panel will store the edge map
panelB = Label(image=edged)
panelB.image = edged
panelB.pack(side="right", padx=10, pady=10)
# otherwise, update the image panels
else:
# update the pannels
panelA.configure(image=image)
panelB.configure(image=edged)
panelA.image = image
panelB.image = edged
def equalizeHistogram(image):
__img = cv.imread(image)
__img = cv.cvtColor(__img, cv.COLOR_BGR2GRAY)
__img = cv.equalizeHist(__img)
__img = cv.cvtColor(__img, cv.COLOR_GRAY2BGR)
return __img
def segmentationBinarizationHist(image):
__img = cv.imread(image)
__img = cv.cvtColor(__img, cv.COLOR_BGR2GRAY)
__img = cv.equalizeHist(__img)
ret, __img = cv.threshold(__img, 128, 255, cv.THRESH_BINARY)
__img = cv.cvtColor(__img, cv.COLOR_GRAY2BGR)
return __img
def equalizeHist(self, path, file_name):
try:
img = cv2.imread(path + file_name)
if session['rg_value'] == 1:
img_yuv = cv2.cvtColor(img, cv2.COLOR_BGR2YUV)
# equalize the histogram of the Y channel
img_yuv[:, :, 0] = cv2.equalizeHist(img_yuv[:, :, 0])
# convert the YUV image back to RGB format
equ = cv2.cvtColor(img_yuv, cv2.COLOR_YUV2BGR)
else:
img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
equ = cv2.equalizeHist(img)
f_name = str(randint(1000000000, 9999999999)) + session['org_name']
session['equalize_file_name'] = f_name
cv2.imwrite(path + f_name, equ)
return f_name
except:
return None
def equalise(path):
"""
CV2 histogram equalise function.
:param path:
:return:
"""
img = cv.imread(path, 0)
equ = cv.equalizeHist(img)
handler.plotFigs([img, equ])
def histograma():
image = grayScale()
equ = cv2.equalizeHist(image)
res = np.hstack((image, equ))
plt.hist(image.ravel(), 256, [0, 256])
plt.hist(res.ravel(), 256, [0, 256])
plt.ion()
plt.show()
def data2img(data,
normalization=1,
histogram=0): # normalization, type castinf(uint8). gray2rgb
if normalization == 1:
data = cv2.normalize(src=data,
dst=None,
beta=0,
alpha=255,
norm_type=cv2.NORM_MINMAX)
data = np.uint8(data)
if histogram == 1:
data = cv2.equalizeHist(data)
if len(data.shape) == 2:
data = np.stack((data, ) * 3, axis=2)
return data
def _get_saturation_edge(self, img):
'''
Get image edges for saturation channel in HSV model.
@img:
np.array, input image.
@return:
np.array, edge image.
'''
hsv = cv.cvtColor(img, cv.COLOR_BGR2HSV)
_, s, _ = cv.split(hsv)
s = cv.equalizeHist(s)
s = cv.GaussianBlur(s, self._gassian_kernel_size, self._gassian_sigma)
s = cv.Canny(s, max(self._canny_param), min(self._canny_param))
return s
def histogram(ImgNo, defThr=127):
img = cv2.imread(impDef.select_img(ImgNo))
img_grayScale = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
hist, bins = np.histogram(img_grayScale.ravel(), 256, [0, 256])
# Numpy를 이용해 히스토그램 구하기
cdf = hist.cumsum()
# numpy배열을 1차원 배열로 변환한 후, 각 멤버값을 누적하여 더한 값을 멤버로 하는 1차원 numpy 배열생성
cdf_m = np.ma.masked_equal(cdf, 0)
# numpy 1차원 배열인 cdf에서 값이 0인 부분은 모두 mask 처리하는 함수. 즉 cdf에서 값이 0인것은 무시
# numpy 1차원 배열 a가 [1, 0, 0, 2]라면 np.ma.masked_equal(a,0)의 값은 [1, --, --, 2] mask로 처리된 부분은 '--
' 으로 표시됨'
cdf_m = (cdf_m - cdf_m.min()) * 255 / (cdf_m.max() - cdf_m.min())
# 히스토그램 균일화 방정식을 코드로 표현
cdf = np.ma.filled(cdf_m, 0).astype('uint8')
# numpy 1차원 배열인 cdf_m에서 마스크된 부분을 0으로 채운 후 numpy 1차원 배열로 리턴
# 위에서 0을 마스크처리한 부분을 복원
img2 = cdf[img_grayScale]
# 원래 이미지에 히스토그램을 적용한 새로운 이미지 img2를 생성
cv2.imshow('Gray Scale', img_grayScale)
cv2.imshow('Histogram Equalization', img2)
#cv2.imwrite('img/Histogram_equal.jpg', img2)
#npImage = np.hstack((img_grayScale, img2))
# img_grayScal과 equ를 수평으로 붙임
#cv2.imshow('numpy Histogram Equalization', npImage)
# OpenCV를 이용한 방법
equ = cv2.equalizeHist(img_grayScale)
# numpy를 이용하여 구현한 것과 동일한 결과를 리턴 함.
# 하지만 numpy는 컬러 이미지에도 적용가능하지만, cv2.equalizeHist()는 grayscal 이미지만 가능하면 리턴도 grayscal 이미지 임
res = np.hstack((img_grayScale, equ))
# img_grayScal과 equ를 수평으로 붙임
cv2.imshow('OpenCV Equalizer', res)
# cv2.imshow('openCV Equalizer', equ)
impDef.close_window()
def apply_histogram(img_n):
img_n = np.array(img_n)
newImg = []
for i in img_n:
img = cv2.normalize(src=i,
dst=None,
alpha=0,
beta=80,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_8U)
equ = cv2.equalizeHist(img)
# res = np.hstack((img, adjusted, equ))
newImg.append(equ.tolist())
return newImg
def pre_dispose(self):#返回一个面上的颜色平均值HSVRGB
img = cv2.GaussianBlur(self.frame,(7,7),0)
b,g,r = cv2.split(img)
avgb = cv2.mean(b)[0]
avgg = cv2.mean(g)[0]
avgr = cv2.mean(r)[0]
k = (avgb+avgg+avgr)/3
kb = k/avgb
kg = k/avgg
kr = k/avgr
b = cv2.addWeighted(src1=b, alpha=kb, src2=0, beta=0, gamma=0)
g = cv2.addWeighted(src1=g, alpha=kg, src2=0, beta=0, gamma=0)
r = cv2.addWeighted(src1=r, alpha=kr, src2=0, beta=0, gamma=0)
img = cv2.merge([b,g,r])
img_hsv = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
h,s,v = cv2.split(img_hsv)
v = cv2.equalizeHist(v)
img_hsv = cv2.merge([h,s,v])
self.img_hsv = img_hsv
img = cv2.cvtColor(img_hsv,cv2.COLOR_HSV2BGR)
self.img_bgr = img
self.frame = img
def save3dBrain(fl, flOut):
curDir = '/home/erika/NormalizacaoCerebro/I36464/'
fileIn = curDir + fl
fileNii = nib.load(fileIn)
img_n = fileNii.get_fdata()
newImg = []
for i in img_n:
img = cv2.normalize(src=i,
dst=None,
alpha=0,
beta=80,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_8U)
equ = cv2.equalizeHist(img)
#res = np.hstack((img, adjusted, equ))
newImg.append(equ.tolist())
newFile = nib.Nifti1Image(np.array(newImg), fileNii.affine)
nib.save(newFile, '/home/erika/Desktop/Resultados tcc/' + flOut)
def msi_to_rgb(in_file, out_file):
ds = gdal.Open(in_file)
rgb = read_as_rgb(ds)
# create_output_image(ds, out_file, rgb)
x = np.dstack(rgb).astype(np.uint8)
H, S, V = cv2.split(cv2.cvtColor(x, cv2.COLOR_RGB2HSV))
eq_V = cv2.equalizeHist(V)
img_output = cv2.cvtColor(cv2.merge([H, S, eq_V]), cv2.COLOR_HSV2RGB)
# x = np.dstack(rgb).astype(np.uint8)
#
# img_yuv = cv2.cvtColor(x, cv2.COLOR_RGB2YUV)
# img_yuv[:,:,0] = cv2.equalizeHist(img_yuv[:,:,0])
# img_output = cv2.cvtColor(img_yuv, cv2.COLOR_YUV2RGB)
#
r = img_output[:, :, 0]
g = img_output[:, :, 1]
b = img_output[:, :, 2]
zzz = [r, g, b]
create_output_image(ds, out_file, zzz)
del ds
def preprocessing(img): img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) img = img.astype(np.uint8) img = cv2.equalizeHist(img) return img
def stereo_sgbm(self):
voice = Voice()
voice.completed.set()
Left_Stereo_Map = (config.left_map1, config.left_map2)
Right_Stereo_Map = (config.right_map1, config.right_map2)
cv.namedWindow("Two Camera")
# cv.namedWindow('depth')
# cv.createTrackbar("windowsize", "depth", 1, 25, lambda x: None)
# cv.createTrackbar("max disp", "depth", 247, 256, lambda x: None)
leftCam = cv.VideoCapture(self.left_camera_id + cv.CAP_DSHOW)
rightCam = cv.VideoCapture(self.right_camera_id + cv.CAP_DSHOW)
leftCam.set(cv.CAP_PROP_FRAME_HEIGHT, self.frameHeight)
leftCam.set(cv.CAP_PROP_FRAME_WIDTH, self.frameWidth)
rightCam.set(cv.CAP_PROP_FRAME_HEIGHT, self.frameHeight)
rightCam.set(cv.CAP_PROP_FRAME_WIDTH, self.frameWidth)
# leftCam.set(cv.CAP_PROP_FPS, 3)
# rightCam.set(cv.CAP_PROP_FPS, 3)
# leftCam.set(cv.CAP_PROP_BUFFERSIZE, 3)
_, fl = leftCam.read()
# window_size = cv.getTrackbarPos("windowsize", "depth")
window_size = 1
# max_disp = cv.getTrackbarPos("max disp", "depth")
max_disp = 247
min_disp = 0
num_disp = max_disp - min_disp
p1_var = 8 * len(fl.shape) * window_size * window_size
p2_var = 32 * len(fl.shape) * window_size * window_size
stereo = cv.StereoSGBM_create(minDisparity=min_disp,
numDisparities=num_disp,
blockSize=window_size,
uniquenessRatio=10,
speckleWindowSize=100,
speckleRange=1,
disp12MaxDiff=10,
P1=p1_var,
P2=p2_var)
# Used for the filtered image
# Create another stereo for right this time
stereoR = cv.ximgproc.createRightMatcher(stereo)
# WLS FILTER Parameters
lmbda = 80000
sigma = 2.0
wls_filter = cv.ximgproc.createDisparityWLSFilter(matcher_left=stereo)
wls_filter.setLambda(lmbda)
wls_filter.setSigmaColor(sigma)
shot = True
if not (leftCam.isOpened() and rightCam.isOpened()):
exit(1)
while True:
retvalOfRight, rightFrame = rightCam.read()
retvalOfLeft, leftFrame = leftCam.read()
if not (retvalOfRight and retvalOfLeft):
print("read fail")
break
key = cv.waitKey(1)
twoFrame = cv.hconcat([rightFrame, leftFrame])
cv.imshow("Two Camera", twoFrame)
if key & 0xFF == ord('q'):
print("結束")
break
# elif key & 0xFF == ord('s'):
elif shot:
frameL = leftFrame
frameR = rightFrame
shot = False
else:
time.sleep(0.1)
shot = True
continue
remapped_left_side = cv.remap(frameL, Left_Stereo_Map[0],
Left_Stereo_Map[1],
cv.INTER_LANCZOS4,
cv.BORDER_CONSTANT, 0)
remapped_right_side = cv.remap(frameR, Right_Stereo_Map[0],
Right_Stereo_Map[1],
cv.INTER_LANCZOS4,
cv.BORDER_CONSTANT, 0)
grayR = cv.cvtColor(remapped_right_side, cv.COLOR_BGR2GRAY)
grayL = cv.cvtColor(remapped_left_side, cv.COLOR_BGR2GRAY)
grayR = cv.equalizeHist(grayR)
grayL = cv.equalizeHist(grayL)
# cv.imshow('grayR', grayR)
# cv.imshow('grayL', grayR)
disp = stereo.compute(grayL, grayR)
dispL = np.int16(disp)
dispR = stereoR.compute(grayR, grayL)
dispR = np.int16(dispR)
# cv.imshow('dispR', dispR)
filteredImg = wls_filter.filter(dispL, grayL, None, dispR)
# cv.imshow('filteredImg', filteredImg)
filteredImg = cv.normalize(src=filteredImg,
dst=filteredImg,
beta=0,
alpha=255,
norm_type=cv.NORM_MINMAX)
filteredImg = np.uint8(filteredImg)
# contours, hierarchy = cv.findContours(filteredImg, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_NONE )
# print(len(contours[0]))
# cv.drawContours(grayL, [cnt], 0, (0,255,0), 3)
# cv.drawContours(filteredImg, contours, 1, (0,0,255), 20)
self.filter_disp = (
(filteredImg.astype(np.float32) / 16) - min_disp) / num_disp
# filt_Color = cv.applyColorMap(filteredImg, cv.COLORMAP_RAINBOW )
# cv.imshow('depth', filt_Color)
cv.imshow('depth', filteredImg)
left = cv.line(remapped_left_side, (0, 0), (0, self.frameHeight),
(0, 0, 0), 1)
self.detect()
if len(self.sentences) == 1:
if voice.completed.is_set():
voice.completed.clear()
voice.say(self.sentences.pop(len(self.sentences) - 1))
cv.imshow('calc', left)
rightCam.release()
leftCam.release()
cv.destroyAllWindows()
voice.terminate()
#-*-coding:utf-8-*-
from cv2 import cv2
import numpy as np
from matplotlib import pyplot as plt
filename = 'snapshot/b8f3506c-3f65-11eb-9798-16f63a1aa8c9.jpg'
# img = cv2.imread('images/watershed.jpg')
img = cv2.imread(filename)
# binaray image로 변환
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (3, 3), 0)
gray = cv2.equalizeHist(gray)
mean = np.average(gray)
ret, thresh1 = cv2.threshold(gray, mean, 255, cv2.THRESH_BINARY_INV)
ret, thresh2 = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY)
# thresh = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,15,4)
thresh = np.bitwise_or(thresh1, thresh2)
#Morphology의 opening, closing을 통해서 노이즈나 Hole제거
kernel = np.ones((3, 3), np.uint8)
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=2)
# dilate를 통해서 확실한 Backgroud
sure_bg = cv2.dilate(opening, kernel, iterations=2)
#distance transform을 적용하면 중심으로 부터 Skeleton Image를 얻을 수 있음.
# 즉, 중심으로 부터 점점 옅어져 가는 영상.
# 그 결과에 thresh를 이용하여 확실한 FG를 파악
def equalizer(image):
if len(image.shape) == 3:
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
eq = cv2.equalizeHist(image)
return eq
def rmReflection(self, bhImage, gsInvertedImg):
img = cv2.add(gsInvertedImg, bhImage)
return cv2.equalizeHist(cv2.medianBlur(img, 5))
right_eye_image_resized = imutils.resize(right_eye_image, width=200)
# Finding centre of left and right eye and
# drawing it on their images
M_left = cv2.moments(leftEye)
cX_left = int(M_left["m10"] / M_left["m00"])
cY_left = int(M_left["m01"] / M_left["m00"])
M_right = cv2.moments(rightEye)
cX_right = int(M_right["m10"] / M_right["m00"])
cY_right = int(M_right["m01"] / M_right["m00"])
cv2.circle(frame, (cX_left, cY_left), 1, (0, 0, 255), -1)
cv2.circle(frame, (cX_right, cY_right), 1, (0, 0, 255), -1)
# Finding Hough Circles in left and right eye images
gray_left = cv2.cvtColor(left_eye_image, cv2.COLOR_BGR2GRAY)
equ_left = cv2.equalizeHist(gray_left)
equ_left_resized = cv2.resize(equ_left, (24, 8),
interpolation=cv2.INTER_AREA)
gray_right = cv2.cvtColor(right_eye_image, cv2.COLOR_BGR2GRAY)
equ_right = cv2.equalizeHist(gray_right)
equ_right_resized = cv2.resize(equ_right, (24, 8),
interpolation=cv2.INTER_AREA)
#circles_left = cv2.HoughCircles(equ_left,cv2.HOUGH_GRADIENT,1,gray_left.shape[0]/8,param1=250,param2=15,minRadius=gray_left.shape[1]/8,maxRadius=gray_left.shape[0]/3)
circles_left = cv2.HoughCircles(equ_left,
cv2.HOUGH_GRADIENT,
1,
20,
param1=50,
param2=30,
minRadius=0,
maxRadius=0)