def train(self, featurefiles, k=100, subsampling=10):
""" Train a vocabulary from features in files listed
in featurefiles using k-means with k number of words.
Subsampling of training data can be used for speedup. """
nbr_images = len(featurefiles)
# read the features from file
descr = []
descr.append(sift.read_features_from_file(featurefiles[0])[1])
descriptors = descr[0] #stack all features for k-means
print("start vstack descriptors")
for i in arange(1, nbr_images):
descr.append(sift.read_features_from_file(featurefiles[i])[1])
descriptors = vstack((descriptors, descr[i]))
# k-means: last number determines number of runs
print("start kmeans")
self.voc, distortion = kmeans(descriptors[::subsampling, :], k, 1)
self.nbr_words = self.voc.shape[0]
# go through all training images and project on vocabulary
imwords = zeros((nbr_images, self.nbr_words))
for i in range(nbr_images):
imwords[i] = self.project(array(descr[i]))
nbr_occurences = sum((imwords > 0) * 1, axis=0)
#http://zhangjunhd.github.io/2014/09/30/text-clustering.html
self.idf = log((1.0 * nbr_images) /
(1.0 * nbr_occurences + 1)) # 这里仅了idf,另外这里写得应该有些问题
self.trainingdata = featurefiles
def get_database(self):
# load vocabulary
with open('vocabulary_bof.pkl', 'rb') as f:
voc = pickle.load(f)
# set index
index = imagesearch.Indexer('index_bof.db', voc)
index.create_tables()
# project features on vocabulary
for i in range(images_num)[:1000]:
locs, descr = sift.read_features_from_file(feature_list[i])
index.add_to_index(image_list[i], descr)
# commit to database
index.db_commit()
con = sqlite.connect('index_bof.db')
print(con.execute('select count (filename) from imlist').fetchone())
print(con.execute('select * from imlist').fetchone())
def bof_image_retrieval(self):
# load vocabulary and query feature
src = self.image_searcher()
q_descr, fp = self.load_query_feature()
# RANSAC model for homography fitting
model = homography.RansacModel()
rank = {}
# query
match_scores = [
w[0] for w in src.query(self.imlist[q_ind])[:nbr_results]
]
res_reg = [w[1] for w in src.query(self.imlist[q_ind])[:nbr_results]]
print('top matches:', res_reg)
self.plot_results(res_reg[:6], match_scores[:6])
if self.bof_rearrange:
# load image features for result
for ndx in res_reg[1:]:
locs, descr = sift.read_features_from_file(self.featlist[ndx])
# get matches
matches = sift.match(q_descr, descr)
ind = matches.nonzero()[0]
ind2 = matches[ind]
locs = np.array(locs)
tp = homography.make_homog(locs[:, :2].T)
# compute homography, count inliers.
try:
H, inliers = homography.H_from_ransac(fp[:, ind],
tp[:, ind2],
model,
match_theshold=4)
except:
inliers = []
# store inlier count
rank[ndx] = len(inliers)
# sort dictionary to get the most inliers first
sorted_rank = sorted(rank.items(),
key=lambda t: t[1],
reverse=True)
res_geom = [res_reg[0]] + [s[0] for s in sorted_rank]
# print('top matches (homography):', res_geom)
# show results
self.plot_results(res_geom[:6], match_scores[:6])
import pickle
from numpy import *
from imagesearch import imagesearch
from localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from tools.imtools import get_imlist
imlist = get_imlist('./first500/')
nbr_images = len(imlist)
featlist = [imlist[i][:-3]+'sift' for i in range(nbr_images)]
f = open('./vocabulary.pkl', 'rb')
voc = pickle.load(f)
f.close()
src = imagesearch.Searcher('web.db',voc)
locs,descr = sift.read_features_from_file(featlist[0])
iw = voc.project(array(descr))
print 'ask using a histogram...'
print src.candidates_from_histogram(iw)[:10]
src = imagesearch.Searcher('web.db',voc)
print 'try a query...'
nbr_results = 12
res = [w[1] for w in src.query(imlist[12])[:nbr_results]]
imagesearch.plot_results(src,res)
def load_query_feature(self):
# load image features for query image
q_locs, q_descr = sift.read_features_from_file(self.featlist[q_ind])
q_locs = np.array(q_locs)
fp = homography.make_homog(q_locs[:, :2].T)
return q_descr, fp
import pickle
from numpy import *
from imagesearch import imagesearch
from localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from tools.imtools import get_imlist
imlist = get_imlist('./first500/')
nbr_images = len(imlist)
featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]
f = open('./vocabulary.pkl', 'rb')
voc = pickle.load(f)
f.close()
src = imagesearch.Searcher('web.db', voc)
locs, descr = sift.read_features_from_file(featlist[0])
iw = voc.project(array(descr))
print 'ask using a histogram...'
print src.candidates_from_histogram(iw)[:10]
src = imagesearch.Searcher('web.db', voc)
print 'try a query...'
nbr_results = 12
res = [w[1] for w in src.query(imlist[12])[:nbr_results]]
imagesearch.plot_results(src, res)
