def get_matches(self, query_image,check_homogenity=False,k=2): good_matches = [] for image in self.images: kp1, des1 = self.sift.detectAndCompute(query_image,None) kp2, des2 = self.sift.detectAndCompute(image,None) # BFMatcher with default params bf = cv2.BFMatcher() matches = bf.knnMatch(des1,des2, k=k) # Apply ratio test good = [] for m,n in matches: if m.distance < 0.75*n.distance: good.append([m]) good_matches.append(len(good)) self.cv = mstatistics.coefficients_of_variation(good_matches) if len(good_matches) == 0: return 0 if check_homogenity: if self.cv <= CV_HOMOGENITY_COEFFICIENT: return mstatistics.mean(good_matches) else: return 0 else: return [mstatistics.mean(good_matches), max(good_matches)]
def get_matches(self, query_image,check_homogenity=False,k=2): good_matches = [] for image in self.images: kp1, des1 = self.sift.detectAndCompute(query_image,None) kp2, des2 = self.sift.detectAndCompute(image,None) FLANN_INDEX_KDTREE = 0 index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5) search_params = dict(checks = 50) flann = cv2.FlannBasedMatcher(index_params, search_params) matches = flann.knnMatch(des1,des2,k=2) good = [] for m,n in matches: if m.distance < 0.7*n.distance: good.append(m) good_matches.append(len(good)) self.cv = mstatistics.coefficients_of_variation(good_matches) if len(good_matches) == 0: return 0 if check_homogenity: if self.cv <= CV_HOMOGENITY_COEFFICIENT: return mstatistics.mean(good_matches) else: return 0 else: return [mstatistics.mean(good_matches), max(good_matches)]
def get_matches(self, query_image, check_homogenity=False, k=2):
good_matches = []
for image in self.images:
kp1, des1 = self.sift.detectAndCompute(query_image, None)
kp2, des2 = self.sift.detectAndCompute(image, None)
# BFMatcher with default params
bf = cv2.BFMatcher()
matches = bf.knnMatch(des1, des2, k=k)
# Apply ratio test
good = []
for m, n in matches:
if m.distance < 0.75 * n.distance:
good.append([m])
good_matches.append(len(good))
self.cv = mstatistics.coefficients_of_variation(good_matches)
if len(good_matches) == 0:
return 0
if check_homogenity:
if self.cv <= CV_HOMOGENITY_COEFFICIENT:
return mstatistics.mean(good_matches)
else:
return 0
else:
return [mstatistics.mean(good_matches), max(good_matches)]
def get_matches(self, query_image, check_homogenity=False, k=2):
good_matches = []
for image in self.images:
kp1, des1 = self.sift.detectAndCompute(query_image, None)
kp2, des2 = self.sift.detectAndCompute(image, None)
FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1, des2, k=2)
good = []
for m, n in matches:
if m.distance < 0.7 * n.distance:
good.append(m)
good_matches.append(len(good))
self.cv = mstatistics.coefficients_of_variation(good_matches)
if len(good_matches) == 0:
return 0
if check_homogenity:
if self.cv <= CV_HOMOGENITY_COEFFICIENT:
return mstatistics.mean(good_matches)
else:
return 0
else:
return [mstatistics.mean(good_matches), max(good_matches)]
def get_matches(self, query_image,check_homogenity=True): matches = [] for image in self.images: kp1, des1 = self.orb.detectAndCompute(query_image,None) kp2, des2 = self.orb.detectAndCompute(image,None) # create BFMatcher object bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True) # Match descriptors. _matches = bf.match(des1,des2) matches.append(len(_matches)) # Sort them in the order of their distance. #_matches = sorted(_matches, key = lambda x:x.distance) if len(matches) == 0: return 0 self.cv = mstatistics.coefficients_of_variation(matches) if check_homogenity: if self.cv <= CV_HOMOGENITY_COEFFICIENT: return mstatistics.mean(matches) else: return 0 else: return [mstatistics.mean(matches), max(matches)]
def get_matches(self, query_image, check_homogenity=True):
matches = []
for image in self.images:
kp1, des1 = self.orb.detectAndCompute(query_image, None)
kp2, des2 = self.orb.detectAndCompute(image, None)
# create BFMatcher object
bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)
# Match descriptors.
_matches = bf.match(des1, des2)
matches.append(len(_matches))
# Sort them in the order of their distance.
#_matches = sorted(_matches, key = lambda x:x.distance)
if len(matches) == 0:
return 0
self.cv = mstatistics.coefficients_of_variation(matches)
if check_homogenity:
if self.cv <= CV_HOMOGENITY_COEFFICIENT:
return mstatistics.mean(matches)
else:
return 0
else:
return [mstatistics.mean(matches), max(matches)]