def get_descriptors(img, imageName, database):
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img = image_enhance.image_enhance(img)
img = np.array(img, dtype=np.uint8)
# Threshold
ret, img = cv2.threshold(img, 127, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
# Thinning
skeleton = skeletonize(img)
skeleton = np.array(skeleton, dtype=np.uint8)
skeleton = removedot(skeleton)
DescriptorList = list()
print("0")
for i in range(0, 399, 133):
print("1")
for j in range(0, 273, 91):
blockImg = img[i:i + 133, j:j + 91]
print("2")
hog = cv2.HOGDescriptor()
hog_des = hog.compute(blockImg)
print("3")
DescriptorList.append(hog_des)
database.update({imageName: DescriptorList})
def get_descriptors(img):
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img = image_enhance.image_enhance(img)
img = numpy.array(img, dtype=numpy.uint8)
# Threshold
ret, img = cv2.threshold(img, 127, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
#Thinning
skeleton = skeletonize(img)
skeleton = numpy.array(skeleton, dtype=numpy.uint8)
skeleton = removedot(skeleton)
# Harris corners
harris_corners = cv2.cornerHarris(img, 3, 3, 0.04)
harris_normalized = cv2.normalize(harris_corners,
0,
255,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_32FC1)
threshold_harris = 125
# Extract keypoints
keypoints = []
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
keypoints.append(cv2.KeyPoint(y, x, 1))
# Define descriptor
orb = cv2.ORB_create()
# Compute descriptors
_, des = orb.compute(img, keypoints)
return (keypoints, des)
def get_descriptors(img):
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
# LIMPIAMOS LA IMAGEN DE RUIDO MEDIANTE UNA LIBRERIA IMAGE_ENHANCE
img = image_enhance.image_enhance(img)
img = numpy.array(img, dtype=numpy.uint8)
# ESCOGEMOS EL MEJOR UMBRAL PARA LA IMAGEN
ret, img = cv2.threshold(img, 127, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
img[img == 255] = 1
# ESQUELETIZAR LA HUELLA PARA TENER MEJOR RESOLUCION
skeleton = skeletonize(img)
skeleton = numpy.array(skeleton, dtype=numpy.uint8)
skeleton = removedot(skeleton)
# DETECTAMOS LOS PUNTOS CRITICOS CON HARRIS
harris_corners = cv2.cornerHarris(img, 3, 3, 0.04)
harris_normalized = cv2.normalize(harris_corners,
0,
255,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_32FC1)
threshold_harris = 125
# EXTRAEMOS LOS PUNTOS CLAVES
keypoints = []
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
keypoints.append(cv2.KeyPoint(y, x, 1))
# DEFINIMOS UN DESCRIPTOR
orb = cv2.ORB_create()
# CALCULAR DESCRIPTOR
_, des = orb.compute(img, keypoints)
return (keypoints, des)
def get_descriptors(img, imageName, database):
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img = image_enhance.image_enhance(img)
img = np.array(img, dtype=np.uint8)
# Threshold
ret, img = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
# Thinning
skeleton = skeletonize(img)
skeleton = np.array(skeleton, dtype=np.uint8)
skeleton = removedot(skeleton)
# Creating Block Size of 144 x 96 total of 8 blocks for an image and then generating descriptors and keypoints
# Storing these 4 descriptors and 8 keypoints of one image in a Mainlist and key(image name) is associated to represent this
# list in a dictionary. So we store all these lists of individual in dictionary and pickling dictionary
# Creating List Format ( [[keypoints][descriptors]]): List initialization
DescriptorList = list()
for i in range(0, 400, 200):
for j in range(0, 274, 137):
blockImg = img[i:i + 200, j:j + 137]
# Harris corners
harris_corners = cv2.cornerHarris(blockImg, 3, 3, 0.04)
harris_normalized = cv2.normalize(harris_corners, 0, 255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32FC1)
threshold_harris = 125;
# Extract keypoints
keypoints = []
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
keypoints.append(cv2.KeyPoint(y, x, 1))
# Define descriptor
orb = cv2.ORB_create()
# Compute descriptors
_, des = orb.compute(blockImg, keypoints)
# pca = PCA(2) # project from 32 to 2 dimensions
# projected = pca.fit_transform(des)
# print(des.shape)
# print(projected.shape)
Reduced_des = PCA(des)
print(type(Reduced_des))
print(Reduced_des.shape)
DescriptorList.append(Reduced_des)
database.update({imageName: DescriptorList})
def get_descriptors(img):
#CLAHE=Contrast Limited Adaptive Histogram Equalization
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img = image_enhance.image_enhance(img)
img = numpy.array(img, dtype=numpy.uint8)
# Threshold
ret, img = cv2.threshold(img, 127, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
img_inv = cv2.bitwise_not(img)
#Thinning
skeleton = skeletonize(img)
skeleton = removedot(skeleton)
skeletonF32 = numpy.float32(skeleton)
# Harris corners= combination of edge and corner detector
harris_corners = cv2.cornerHarris(skeletonF32, 3, 3, 0.04)
harris_normalized = cv2.normalize(harris_corners,
0,
255,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_32FC1)
threshold_harris = 125
# Extract keypoints
keypoints = []
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
keypoints.append(cv2.KeyPoint(y, x, 1))
# Define descriptor
orb = cv2.ORB_create()
# Compute descriptors
_, des = orb.compute(img, keypoints)
return (skeleton, keypoints, des)
def get_descriptors(img):
i = random.randint(0, 1000)
# Apply Clahe
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img1 = img * 255
a = "CLAHE" + str(i)
# cv2.imshow("Clahe",img)
cv2.imwrite(f"./static/img/{a}.png", img1)
# Enhance image
img = image_enhance.image_enhance(img)
img = numpy.array(img, dtype=numpy.uint8)
# cv2.imshow("enhance",255*img)
img2 = img * 255
b = "Enhance" + str(i)
cv2.imwrite(f"./static/img/{b}.png", img2)
# Threshold
ret, img = cv2.threshold(img, 127, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
img3 = img
c = "Normalize" + str(i)
# cv2.imshow("Threshold",img)
cv2.imwrite(f"./static/img/{c}.png", img3)
# plot_figure(img1,img2,img3,a,b,c)
#Skeleton & Thinning
skeleton = skeletonize(img)
img1 = skeleton * 255
a = "Skeleton" + str(i)
cv2.imwrite(f"./static/img/{a}.png", img1)
skeleton = numpy.array(skeleton, dtype=numpy.uint8)
#cv2.imshow("skeleton",skeleton)
skeleton = removedot(skeleton)
img2 = skeleton * 255
b = "Thinning" + str(i)
#cv2.imwrite(f"./static/img/{b}.png",img2)
# Harris corners
harris_corners = cv2.cornerHarris(img, 3, 3, 0.04)
harris_normalized = cv2.normalize(harris_corners,
0,
255,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_32FC1)
threshold_harris = 125
# Extract keypoints
keypoints = []
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
#print(x,y)
keypoints.append(cv2.KeyPoint(y, x, 1))
img3 = cv2.drawKeypoints(img, keypoints, outImage=None)
c = "Keypoints" + str(i)
# plot_figure(img1,img2,img3,a,b,c)
cv2.imwrite(f"./static/img/{c}.png", img3)
# Define descriptor
orb = cv2.ORB_create()
# Compute descriptors
_, des = orb.compute(img, keypoints)
return (keypoints, des)
def get_descriptors(img, imageName, database, KeypointsLength):
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img = image_enhance.image_enhance(img)
img = np.array(img, dtype=np.uint8)
# Threshold
ret, img = cv2.threshold(img, 127, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
# Thinning
skeleton = skeletonize(img)
skeleton = np.array(skeleton, dtype=np.uint8)
skeleton = removedot(skeleton)
# Creating Block Size of 144 x 96 total of 8 blocks for an image and then generating descriptors and keypoints
# Storing these 4 descriptors and 8 keypoints of one image in a Mainlist and key(image name) is associated to represent this
# list in a dictionary. So we store all these lists of individual in dictionary and pickling dictionary
# Creating List Format ( [[keypoints][descriptors]]): List initialization
DescriptorList = list()
imageiter = 1
InnerList = list()
for i in range(0, 399, 133):
for j in range(0, 273, 91):
blockImg = img[i:i + 133, j:j + 91]
# Harris corners
harris_corners = cv2.cornerHarris(blockImg, 3, 3, 0.04)
harris_normalized = cv2.normalize(harris_corners,
0,
255,
norm_type=cv2.NORM_MINMAX,
dtype=cv2.CV_32FC1)
threshold_harris = 125
# Extract keypoints
KeypointsList = []
blockKeypoints = list()
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
blockKeypoints.append(cv2.KeyPoint(y, x, 1))
# Define descriptor
orb = cv2.ORB_create()
# Compute descriptors
_, blockDescriptors = orb.compute(blockImg, blockKeypoints)
KeypointsList.append(blockKeypoints)
DescriptorList.append(blockDescriptors)
os.chdir("E:\ML\Fingerprint ML Project\Fingerprint\Image_Blocks")
blockImg[blockImg == 1] = 255
InnerList.append(len(blockKeypoints))
if imageiter == 5:
Kimg = cv2.drawKeypoints(blockImg,
blockKeypoints,
outImage=None)
return Kimg
imageiter += 1
KeypointsLength.append(InnerList)
