vocab_func.py

def developVocabulary(self,n_images, descriptor_list, kmeans_ret = None):
		
		"""
		Each cluster denotes a particular visual word 
		Every image can be represeted as a combination of multiple 
		visual words. The best method is to generate a sparse histogram
		that contains the frequency of occurence of each visual word 

		Thus the vocabulary comprises of a set of histograms of encompassing
		all descriptions for all images

		"""

		self.mega_histogram = np.array([np.zeros(self.n_clusters) for i in range(n_images)])
		old_count = 0
		for i in range(n_images):
			l = len(descriptor_list[i])
			for j in range(l):
				if kmeans_ret is None:
					idx = self.kmeans_ret[old_count+j]
				else:
					idx = kmeans_ret[old_count+j]
				self.mega_histogram[i][idx] += 1
			old_count += l
		print "Vocabulary Histogram Generated"