bag-of-words_词袋图像检索_词袋模型_python_bagofvisualwords_bagofwords_

#python2.7 #python findFeatures.py -t dataset/train/ import argparse as ap import cv2 import numpy as np import os from sklearn.externals import joblib from scipy.cluster.vq import * from sklearn import preprocessing import math # Get the path of the training set 获取训练集路径 parser = ap.ArgumentParser() parser.add_argument("-t", "--trainingSet", help="Path to Training Set", required="True") args = vars(parser.parse_args()) # Get the training classes names and store them in a list 获取训练路径名并将其存入list train_path = args["trainingSet"] training_names = os.listdir(train_path) numWords = 64 # 聚类中心数 # Get all the path to the images and save them in a list 获取所有图片的路径存入list # image_paths and the corresponding label in image_paths image_paths = [] # 所有图片路径 for training_name in training_names: image_path = os.path.join(train_path, training_name) #路径拼接 image_paths += [image_path] # Create feature extraction and keypoint detector objects 创建SIFT特征提取对象和关键点检测对象 sift = cv2.xfeatures2d.SIFT_create() # List where all the descriptors are stored 特征描述 des_list = [] for i, image_path in enumerate(image_paths): im = cv2.imread(image_path) # 读取图片数据 print "Extract SIFT of %s image, %d of %d images" %(training_names[i], i, len(image_paths)) #提取共m张图片中的第n张图片的SIFT特征 kpts = sift.detect(im) #提取关键点 kpts, des = sift.compute(im, kpts) #使用关键点找出sift特征向量 des_list.append((image_path, des)) # Stack all the descriptors vertically in a numpy array #downsampling = 1 #descriptors = des_list[0][1][::downsampling,:] #for image_path, descriptor in des_list[1:]: # descriptors = np.vstack((descriptors, descriptor[::downsampling,:])) # Stack all the descriptors vertically in a numpy array 将所有特征描述存放在一个列矩阵中 descriptors = des_list[0][1] print('生成向量数组') for image_path, descriptor in des_list[1:]: descriptors = np.vstack((descriptors, descriptor)) #垂直方向叠加 # Perform k-means clustering 执行k-means聚类 print "Start k-means: %d words, %d key points" %(numWords, descriptors.shape[0]) voc, variance = kmeans(descriptors, numWords, 1) # Calculate the histogram of features 计算特征直方图 im_features = np.zeros((len(image_paths), numWords), "float32") for i in xrange(len(image_paths)): words, distance = vq(des_list[i][1],voc) for w in words: im_features[i][w] += 1 # Perform Tf-Idf vectorization 得到id-idf向量 nbr_occurences = np.sum( (im_features > 0) * 1, axis = 0) idf = np.array(np.log((1.0*len(image_paths)+1) / (1.0*nbr_occurences + 1)), 'float32') # Perform L2 normalization L2归一化 im_features = im_features*idf im_features = preprocessing.normalize(im_features, norm='l2') # 将训练的模型保存到本地 print('保存词袋模型文件') joblib.dump((im_features, image_paths, idf, numWords, voc), "bof.pkl", compress=3)