def match_sift(sift1,sift2, dist_thresh = 1.1):
matches = -1 * np.ones((sift1.shape[0]), 'int')
# FIRST NORMALIZE SIFT VECTORS
sift1 = tools.normalizeL2(sift1, 0)
sift2 = tools.normalizeL2(sift2, 0)
sift2transp = sift2.T
# loop through all sift1 features
for i in range(len(sift1)):
# make sure vars are empty before looping. canopy rules
dist_sift = []
dist_sift_sort = []
# compute distance for each sift1 vector with all sift2 vectors and keep track of distances in dist_sift
dist_sift = dot(sift1[i], sift2transp)
# sort all found distances to get the 2 best matches
dist_sift_sort = np.argsort(dist_sift)
# since the matches are the highest ones, they're at the end of the sorted array
dist_frst = (len(dist_sift)-1)
dist_scnd = (len(dist_sift)-2)
# apply Lowe's match criterion
if (dist_sift[dist_sift_sort[dist_frst]] / dist_sift[dist_sift_sort[dist_scnd]]) > dist_thresh:
# seems we've found a match for feature sift1[i]
# adding the sift2 index to our match array
matches[i] = dist_sift_sort[dist_frst]
#else:
# no match for sift1[i] in sift2.
# so no kudos for this one
#matches[i] = -1
# FOR ALL FEATURES IN SIFT1 FIND THE 2 CLOSEST FEATURES IN SIFT2
#for i in sift1:
# IF SIFT1_i IS MUCH CLOSER TO SIFT2_j1 THAN SIFT2_j2, THEN CONSIDER THIS A MUCH
# MUCH CLOSER MEANS MORE THAN A PREDEFINED DISTANCE THRESHOLD
return matches
def match_sift(sift1, sift2, dist_thresh=1.1):
global CACHING, WRITTEN_TO_CACHE, RENEW_CACHE
if CACHING:
h1 = arrayhash(sift1)
h2 = arrayhash(sift2)
if (h1, h2) in cache['match_sift']:
print "retrieving from cache: 'match_sift'"
return cache['match_sift'][h1, h2]
matches = -1 * np.ones((sift1.shape[0]), 'int')
# FIRST NORMALIZE SIFT VECTORS
sift1 = tools.normalizeL2(sift1, 0)
sift2 = tools.normalizeL2(sift2, 0)
# FOR ALL FEATURES IN SIFT1 FIND THE 2 CLOSEST FEATURES IN SIFT2
# IF SIFT1_i IS MUCH CLOSER TO SIFT2_j1 THAN SIFT2_j2, THEN CONSIDER THIS
# A MUCH MUCH CLOSER MEANS MORE THAN A PREDEFINED DISTANCE THRESHOLD
dists = np.zeros(sift2.shape[0], 'float')
ranked_ratio = float('infinity') * np.ones(sift1.shape[0], 'float')
dist_l2 = lambda x, y: float(x * y)
for i, s1 in enumerate(sift1):
for j, s2 in enumerate(sift2):
dists[j] = sum(map(dist_l2, s1, s2))
closest_id = np.argmin(dists)
closest = dists[closest_id]
dists[closest_id] = float('infinity')
second_closest = np.amin(dists)
if closest / float(second_closest) < dist_thresh:
matches[i] = closest_id
ranked_ratio[i] = closest / float(second_closest)
matches[i] = closest_id
cache['match_sift'][arrayhash(sift1), arrayhash(sift2)] \
= matches, ranked_ratio
WRITTEN_TO_CACHE = True
return matches, ranked_ratio
def match_sift(sift1,sift2, dist_thresh = 2.0):
matches = -1 * np.ones((sift1.shape[0]), 'int')
# FIRST NORMALIZE SIFT VECTORS
sift1 = tools.normalizeL1(sift1, 0)
sift2 = tools.normalizeL2(sift1, 0)
# FOR ALL FEATURES IN SIFT1 FIND THE 2 CLOSEST FEATURES IN SIFT2
N1 = sift1.shape[0]
N2 = sift2.shape[0]
matches = -1 * np.ones((sift1.shape[0]), 'int')
dist = np.dot(sift1, sift2.T)
for i in range(0, N1):
temp = dist[i,:]
indx = np.argsort(temp)
indx = indx[::-1]
if temp[indx[0]] / temp[indx[1]] > dist_thresh:
matches[i] = indx[0]
# IF SIFT1_i IS MUCH CLOSER TO SIFT2_j1 THAN SIFT2_j2, THEN CONSIDER THIS A MUCH
# MUCH CLOSER MEANS MORE THAN A PREDEFINED DISTANCE THRESHOLD
return matches
impath2 = '../../data/oxford_scaled/all_souls_000076.jpg'
frames2, sift2 = week2.compute_sift(impath2)
figure(1)
subplot(1, 2, 1)
im1 = Image.open(impath1)
week2.plot_features(im1, frames1, False, 'r')
subplot(1, 2, 2)
im2 = Image.open(impath2)
week2.plot_features(im2, frames2, False, 'r')
# STEP C.1 NORMALIZE SIFT VECTORS
DEFINE_AXIS=0
sift1 = tools.normalizeL2(sift1, DEFINE_AXIS)
sift2 = tools.normalizeL2(sift2, DEFINE_AXIS)
threshold = 1.1
# setup our array of matches
matches = np.zeros(len(sift1))
sift2transp = sift2.T
# loop through all sift1 features
for i in range(len(sift1)):
# make sure vars are empty before looping. canopy rules
dist_sift = []
dist_sift_sort = []l
# compute distance for each sift1 vector with all sift2 vectors and keep track of distances in dist_sift
impath1 = '../../data/oxford_scaled/all_souls_000026.jpg'
frames1, sift1 = week2.compute_sift(impath1)
impath2 = '../../data/oxford_scaled/all_souls_000068.jpg'
frames2, sift2 = week2.compute_sift(impath2)
figure(1)
subplot(1, 2, 1)
im1 = Image.open(impath1)
week2.plot_features(im1, frames1, False, 'r')
subplot(1, 2, 2)
im2 = Image.open(impath2)
week2.plot_features(im2, frames2, False, 'r')
# STEP C.1 NORMALIZE SIFT VECTORS
sift1 = tools.normalizeL2(sift1, 1)
sift2 = tools.normalizeL2(sift2, 1)
# STEP C.2 COMPUTE DISTANCES BETWEEN ALL VECTORS IN SIFT1 AND SIFT2.
N1 = sift1.shape[0]
N2 = sift2.shape[0]
dist_thresh = 1.1
matches = -1 * np.ones((sift1.shape[0]), 'int')
dist = np.dot(sift1, sift2.T)
for i in range(0, N1):
temp = dist[i,:]
indx = np.argsort(temp)
indx = indx[::-1]
if temp[indx[0]] / temp[indx[1]] > dist_thresh:
bows.append(week3.load_bow(CODEBOOK_DIR + files[i]))
# PART 5. STEP 2. COMPUTE DISTANCE MATRIX
# setup matrix for comparison outcomes. 0,0 = img1,img1, 0,1=img1,img2
bowdists = np.zeros((len(bows), len(bows)))
# setup check matrix to keep track of comparisons already done. set to 1 if done
bowcheck = np.zeros((len(bows), len(bows)))
# reset for canopy...
bowdiststorage = 0
x = -1
for bw1 in bows:
x += 1
y = -1
bw1n = tools.normalizeL2(bw1) # for l2 distance
#bw1n = tools.normalizeL1(bw1) # for intersect distance
for bw2 in bows:
bowdiststorage = 0
y += 1
if bowcheck[x,y] == 0 and bowcheck[y,x] == 0:
# new bow distance
bowcheck[x,y] = 1
bowcheck[y,x] = 1
bw2n = tools.normalizeL2(bw2) # for l2 distance
#bw2n = tools.normalizeL1(bw2) # for intersect distance
bowdiststorage = week3.computeVectorDistance(bw1n, bw2n, DISTANCE)
bowdists[x,y] = bowdiststorage
bowdists[y,x] = bowdiststorage
# PART 5. STEP 3. PERFORM RANKING SIMILAR TO WEEK 1 & 2 WITH QUERIES 'all_souls_000065.jpg', 'all_souls_0000XX.jpg', 'all_souls_0000XX.jpg'
# PART 5. STEP 1. LOAD BAG-OF-WORDS VECTORS FROM ../../data/bow/codebook_100/ using the week3.load_bow function
files = os.listdir('../../data/bow/codebook_100/')
bows = []
for f in files:
bows.append(week3.load_bow('../../data/bow/codebook_100/' + f))
# PART 5. STEP 2. COMPUTE DISTANCE MATRIX
dist = []
dist_type = 'intersect'
dist = np.zeros(len(files)**2).reshape((len(files),len(files)))
for i in range(0,len(files)):
for j in range(0,len(files)):
if dist_type == 'euclidean' or dist_type == 'l2':
dist[i][j] = sum(((bows[i][k] - bows[j][k])**2) for k in range(len(bows[i])))
tools.normalizeL2(dist[i][j])
elif dist_type == 'intersect' or dist_type == 'l1':
dist[i][j] = sum((np.minimum(bows[i][k], bows[j][k])) for k in range(len(bows[i])))
tools.normalizeL1(dist[i][j])
elif dist_type == 'chi2':
dist[i][j] = sum((((bows[i][k] - bows[j][k]) **2) / (bows[i][k]+bows[j][k])) for k in range(len(bows[i])))
elif dist_type == 'hellinger':
dist[i][j] = sum((np.sqrt((bows[i][k]*bows[j][k]))) for k in range(len(bows[i])))
tools.normalizeL2(dist[i][j])
print dist[i][j]
# PART 5. STEP 3. PERFORM RANKING SIMILAR TO WEEK 1 & 2 WITH QUERIES 'all_souls_000065.jpg', 'all_souls_0000XX.jpg', 'all_souls_0000XX.jpg'
query_id = int(89) #89, 21, 48
ranking = np.argsort(dist[query_id])
