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(sift1.read_features_from_file(featurefiles[0])[1])
descriptors = descr[0] #stack all features for k-means
for i in arange(1,nbr_images):
descr.append(sift1.read_features_from_file(featurefiles[i])[1])
descriptors = vstack((descriptors,descr[i]))
# k-means: last number determines number of runs
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(descr[i])
nbr_occurences = sum( (imwords > 0)*1 ,axis=0)
self.idf = log( (1.0*nbr_images) / (1.0*nbr_occurences+1) )
self.trainingdata = featurefiles
# index of query image and number of results to return
q_ind=0
nbr_results=8
# regular query
res_reg = [w[1] for w in src.query(newimlist[q_ind])[:nbr_results]]
print 'top matches (regular):',res_reg
print newimlist[1]
# load image features from query image
q_locs,q_descr=sift1.read_features_from_file(featlist[q_ind])
fp=homography.make_homog(q_locs[:,:2].T)
# RANSAC model for homography fitting
model = homography.RansacModel()
rank={}
# load image features for result
for ndx in res_reg[1:]:
print ndx
locs,descr = sift1.read_features_from_file(featlist[ndx])
imlist=get_imlist('img')
nbr_images = len(imlist)
featlist = [ imlist[i][:-3]+'sift' for i in range(nbr_images) ]
newimlist=[]
for i in imlist:
newimlist.append(i[4:])
# load vocabulary
with open('vocabulary.pkl','rb') as f:
voc=pickle.load(f)
# create indexer
indx = new_imagesearch.Indexer('test.db',voc)
"""Uncomment when you need to recreate the database"""
#indx.create_tables()
""" End"""
# Add images to database
for i in range(nbr_images):
locs,descr=sift1.read_features_from_file(featlist[i])
indx.add_to_index(newimlist[i],descr)
indx.db_commit()