基于bag of words的图像检索基本步骤
- 特征提取
- 学习 “视觉词典
- 针对输入特征集,根据视觉词典进行量化
- 把输入图像转化成视觉单词的频率直方图
5.构造特征到图像的倒排表,通过倒排表快速索引相关图像
6.根据索引结果进行直方图匹配
代码及运行结果
获取特征,生成词汇
import pickle
from PCV.imagesearch import vocabulary
from PCV.tools.imtools import get_imlist
from PCV.localdescriptors import sift
##要记得将PCV放置在对应的路径下
#获取图像列表
imlist = get_imlist('first1000/') ###要记得改成自己的路径
nbr_images = len(imlist)
#获取特征列表
featlist = [imlist[i][:-3]+'sift' for i in range(nbr_images)]
#提取文件夹下图像的sift特征
for i in range(nbr_images):sift.process_image(imlist[i], featlist[i])
#生成词汇
voc = vocabulary.Vocabulary('ukbenchtest')
voc.train(featlist, 1000, 10)
#保存词汇
# saving vocabulary
with open('first1000/vocabulary.pkl', 'wb') as f:pickle.dump(voc, f)
print ('vocabulary is:', voc.name, voc.nbr_words)
生成词典
import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
from sqlite3 import dbapi2 as sqlite
from PCV.tools.imtools import get_imlist
##要记得将PCV放置在对应的路径下
##要记得将PCV放置在对应的路径下
#获取图像列表
imlist = get_imlist('first1000/')##记得改成自己的路径
nbr_images = len(imlist)
#获取特征列表
featlist = [imlist[i][:-3]+'sift' for i in range(nbr_images)]
# load vocabulary
#载入词汇
with open('first1000/vocabulary.pkl', 'rb') as f:voc = pickle.load(f)
#创建索引
indx = imagesearch.Indexer('testImaAdd.db',voc)
indx.create_tables()
# go through all images, project features on vocabulary and insert
#遍历所有的图像,并将它们的特征投影到词汇上
for i in range(nbr_images)[:1000]:locs,descr = sift.read_features_from_file(featlist[i])
indx.add_to_index(imlist[i],descr)
# commit to database
#提交到数据库
indx.db_commit()
con = sqlite.connect('testImaAdd.db')
print (con.execute('select count (filename) from imlist').fetchone())
print (con.execute('select * from imlist').fetchone())
搜索结果
import pickle
from PCV.localdescriptors import sift
from PCV.imagesearch import imagesearch
from PCV.geometry import homography
from PCV.tools.imtools import get_imlist
# load image list and vocabulary
#载入图像列表
imlist = get_imlist('first1000/')
nbr_images = len(imlist)
#载入特征列表
featlist = [imlist[i][:-3]+'sift' for i in range(nbr_images)]
#载入词汇
with open('first1000/vocabulary.pkl', 'rb') as f:
voc = pickle.load(f)
src = imagesearch.Searcher('testImaAdd.db',voc)
# index of query image and number of results to return
#查询图像索引和查询返回的图像数
q_ind = 0
nbr_results = 20
# regular query
# 常规查询(按欧式距离对结果排序)
res_reg = [w[1] for w in src.query(imlist[q_ind])[:nbr_results]]
print ('top matches (regular):', res_reg)
# load image features for query image
#载入查询图像特征
q_locs,q_descr = sift.read_features_from_file(featlist[q_ind])
fp = homography.make_homog(q_locs[:,:2].T)
# RANSAC model for homography fitting
#用单应性进行拟合建立RANSAC模型
model = homography.RansacModel()
rank = {}
# load image features for result
#载入候选图像的特征
for ndx in res_reg[1:]:
locs,descr = sift.read_features_from_file(featlist[ndx]) # because 'ndx' is a rowid of the DB that starts at 1
# get matches
matches = sift.match(q_descr,descr)
ind = matches.nonzero()[0]
ind2 = matches[ind]
tp = homography.make_homog(locs[:,:2].T)
# compute homography, count inliers. if not enough matches return empty list
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)
# 显示查询结果
imagesearch.plot_results(src,res_reg[:8]) #常规查询
imagesearch.plot_results(src,res_geom[:8]) #重排后的结果
运行结果