def sobelDetection(self, img):
print(img)
Sx = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]])
Sy = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]])
img_x = conv(img, Sx)
img_y = conv(img, Sy)
img_out = np.sqrt(img_x * img_x + img_y * img_y)
img_out = np.ceil((img_out / np.max(img_out)) * 255)
plt.imshow(img_out, cmap="gray", interpolation="bicubic")
plt.xticks([]), plt.yticks([])
plt.show()
def SobelClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
Sx = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]])
Sy = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]])
img_x = conv(img, Sx) / 8.0
img_y = conv(img, Sy) / 8.0
img_out = np.sqrt(np.power(img_x, 2) + np.power(img_y, 2))
img_out = (img_out / np.max(img_out)) * 255
self.image = img
self.displayImage(2)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([]), plt.yticks([]) # to hide tick values on X and Y axis
plt.show()
def CannyClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
h,w=img.shape[:2]
#step 1: reduce noise with Gaussian Filter
gauss = (1.0 / 57) * np.array(
[[0, 1, 2, 1, 0],
[1, 3, 5, 3, 1],
[2, 5, 9, 5, 2],
[1, 3, 5, 3, 1],
[0, 1, 2, 1, 0]])
img_blur = conv(img, gauss)
#step 2: Finding Gradien
img_x=conv(img_blur,np.array([[-0.5,0,0.5]]))
img_y=conv(img_blur,np.array([[-0.5,0,0.5]]))
E_mag=np.sqrt(np.power(img_x,2)+np.power(img_y,2))
E_mag=(E_mag/np.max(E_mag))*255
#step 3: non-maximum suppresion
t_low=4
E_nms=np.zeros((h,w))
for i in np.arange(1,h-1):
for j in np.arange(1,w-1):
dx=img_x[i,j]
dy=img_y[i,j]
s_theta=fg.FindingGradien(dx,dy)
if locmax.MaxSuppesion(E_mag,i,j,s_theta,t_low):
E_nms[i,j]=E_mag[i,j]
#step 4: Hysterisis Thresholding
t_high=15
E_bin=np.zeros((h,w))
for i in np.arange(1,h-1):
for j in np.arange(1,w-1):
if E_nms[i,j]>=t_high and E_bin[i,j]==0:
ht.HysterisisThres(E_nms,E_bin,i,j,t_low)
self.image=img
self.displayImage(2)
plt.imshow(E_bin,cmap='gray', interpolation='bicubic')
plt.xticks([]),plt.yticks([])
plt.show()
def PrewitClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
Px = np.array([[-1, 0, 1], [-1, 0, 1], [-1, 0, 1]])
Py = np.array([[-1, -1, -1], [0, 0, 0], [1, 1, 1]])
img_x = conv(img, Px)
img_y = conv(img, Py)
img_out = np.sqrt((img_x * img_x) + (img_y * img_y))
img_out = (img_out / np.max(img_out)) * 255
self.image = img
self.displayImage(2)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([]), plt.yticks([]) # to hide tick values on X and Y axis
plt.show()
def SharpeningClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
gauss = (1.0 / 16) * np.array(
[[1, -2, 1],
[-2, 5, -2],
[1, -2, 1]])
img_out = conv(img, gauss)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([], plt.yticks([]))
plt.show()
def MeanClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
gauss = (1.0 / 57) * np.array(
[[1/9, 1/9, 1/9],
[1/9, 1/9, 1/9],
[1/9, 1/9, 1/9]])
img_out = conv(img, gauss)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([], plt.yticks([]))
plt.show()
def MeanClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
laplace = (1.0 / 9) * np.array([[1, 1, 1, 1, 1], [1, 1, 1, 1, 1],
[1, 1, 1, 1, 1], [1, 1, 1, 1, 1],
[1, 1, 1, 1, 1]])
img_out = conv(img, laplace)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([], plt.yticks([]))
plt.show()
def SharpClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
laplace = (1.0 / 16) * np.array([[0, 0, -1, 0, 0], [0, -1, -2, -1, 0],
[-1, -2, 16, -2, -1],
[0, -1, -2, -1, 0], [0, 0, -1, 0, 0]])
img_out = conv(img, laplace)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([], plt.yticks([]))
plt.show()
def GaussianClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
gauss = (1.0 / 57) * np.array(
[[0.0029, 0.0131, 0.0215, 0.0131, 0.0029],
[0.0131, 0.0585, 0.0965, 0.0585, 0.0131],
[0.0215, 0.0965, 0.1592, 0.0965, 0.0215],
[0.0131, 0.0585, 0.0965, 0.0585, 0.0131],
[0.0029, 0.0131, 0.0215, 0.0131, 0.0029]])
img_out = conv(img, gauss)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([], plt.yticks([]))
plt.show()
def SmoothClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
#h,w=img.shape[:2]
gauss = (1.0 / 57) * np.array([[0, 1, 2, 1, 0], [1, 3, 5, 3, 1],
[2, 5, 9, 5, 2], [1, 3, 5, 3, 1],
[0, 1, 2, 1, 0]])
img_out = conv(img, gauss)
#
# #cv2.imshow('',img_out)
# self.image=img_out
# self.displayImage(i)
plt.imshow(img_out, cmap='gray', interpolation='bicubic')
plt.xticks([], plt.yticks([]))
plt.show()
def CannyClicked(self):
img = cv2.cvtColor(self.image, cv2.COLOR_BGR2GRAY)
gaus = (1.0 / 9) * np.array([[1, 1, 1], [1, 1, 1], [1, 1, 1]])
img_gaus = conv(img, gaus)
# ubah format gambar
img_gaus = img_gaus.astype("uint8")
cv2.imshow("gaus",img_gaus)
#sobel
Sx = np.array([[-1, 0, 1],
[-2, 0, 2],
[-1, 0, 1]])
Sy = np.array([[-1, -2, -1],
[0, 0, 0],
[1, 2, 1]])
img_x = conv(img_gaus, Sx)
img_y = conv(img_gaus, Sy)
H, W = img.shape[:2]
img_out = np.zeros((H, W))
for i in np.arange(H):
for j in np.arange(W):
x = img_x.item(i, j)
y = img_y.item(i, j)
hasil = np.abs(x) + np.abs(y)
if (hasil > 255):
hasil = 255
if (hasil < 0):
hasil = 0
else:
hasil = hasil
img_out.itemset((i, j), hasil)
# hasil gradient
img_out = img_out.astype("uint8")
#arah tepi
theta = np.arctan2(img_y, img_x)
cv2.imshow("sobel",img_out)
#non-max supresion
Z = np.zeros((H, W), dtype=np.int32)
angle = theta * 180. / np.pi
angle[angle < 0] += 180
for i in range(1, H - 1):
for j in range(1, W - 1):
try:
q = 255
r = 255
# angle 0
if (0 <= angle[i, j] < 22.5) or (157.5 <= angle[i, j] <= 180):
q = img_out[i, j + 1]
r = img_out[i, j - 1]
# angle 45
elif (22.5 <= angle[i, j] < 67.5):
q = img_out[i + 1, j - 1]
r = img_out[i - 1, j + 1]
# angle 90
elif (67.5 <= angle[i, j] < 112.5):
q = img_out[i + 1, j]
r = img_out[i - 1, j]
# angle 135
elif (112.5 <= angle[i, j] < 157.5):
q = img_out[i - 1, j - 1]
r = img_out[i + 1, j + 1]
if (img_out[i, j] >= q) and (img_out[i, j] >= r):
Z[i, j] = img_out[i, j]
else:
Z[i, j] = 0
except IndexError as e:
pass
img_N = Z.astype("uint8")
cv2.imshow("NON", img_N)
# hysteresis Thresholding menentukan tepi lemah dan kuat
weak = 50
strong = 100
for i in np.arange(H):
for j in np.arange(W):
a = img_N.item(i, j)
if (a > weak) : #weak
b = weak
if (a > strong): #strong
b = 255
else:
b = 0
img_N.itemset((i, j), b)
img_H1 = img_N.astype("uint8")
cv2.imshow("hysteresis part 1", img_H1)
# hysteresis Thresholding eliminasi titik tepi lemah jika tidak terhubung dengan tetangga tepi kuat
strong = 255
for i in range(1, H - 1):
for j in range(1, W - 1):
if (img_H1[i, j] == weak):
try:
if ((img_H1[i + 1, j - 1] == strong) or
(img_H1[i + 1, j] == strong) or
(img_H1[i + 1, j + 1] == strong) or
(img_H1[i, j - 1] == strong) or
(img_H1[i, j + 1] == strong) or
(img_H1[i - 1, j - 1] == strong) or
(img_H1[i - 1, j] == strong) or (img_H1[i - 1, j + 1] == strong)):
img_H1[i, j] = strong
else:
img_H1[i, j] = 0
except IndexError as e:
pass
img_H2 = img_H1.astype("uint8")
cv2.imshow("Canny Edge Detection", img_H2)
