PythonComputerVision-7-ImageSearch

一.基于内容的图像检索

1.矢量空间模型

二.视觉单词

1.BOW模型

2.创建词汇

三.图像索引

1.建立数据库

2.添加图像

四.在数据库中搜索图像

1.利用索引获取候选图像

2.用一幅图像进行查询

3.确定对比基准并绘制结果

五.使用几何特性对结果排序

六.演示程序及Web应用

1.所需运行环境及相应配置

2.源码及流程

1)生成所需模型文件

# -*- coding: utf-8 -*-
import pickle
from PCV.imagesearch import vocabulary
from PCV.tools.imtools import get_imlist
from PCV.localdescriptors import sift
#获取图像列表
imlist = get_imlist('first1000/')
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)

2)将模型数据导入数据库

# -*- coding: utf-8 -*-
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
#获取图像列表
imlist = get_imlist('first1000/')
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())
 

3).索引测试

# -*- coding: utf-8 -*-
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

4).建立Demo和Web应用

# -*- coding: utf-8 -*-
import cherrypy
import pickle
import urllib
import os
from numpy import *
#from PCV.tools.imtools import get_imlist
from PCV.imagesearch import imagesearch
import random
"""
This is the image search demo in Section 7.6.
"""
class SearchDemo:
 def __init__(self):
 # 载入图像列表
 self.path = 'first1000/'
 #self.path = 'D:/python_web/isoutu/first500/'
 self.imlist = [os.path.join(self.path,f) for f in os.listdir(self.path) if f.endswith('.jpg')]
 #self.imlist = get_imlist('./first500/')
 #self.imlist = get_imlist('E:/python/isoutu/first500/')
 self.nbr_images = len(self.imlist)
 print (self.imlist)
 print (self.nbr_images)
 self.ndx = list(range(self.nbr_images))
 print (self.ndx)
 # 载入词汇
 # f = open('first1000/vocabulary.pkl', 'rb')
 with open('first1000/vocabulary.pkl','rb') as f:
 self.voc = pickle.load(f)
 #f.close()
 # 显示搜索返回的图像数
 self.maxres = 10
 # header and footer html
 self.header = """
 <!doctype html>
 <head>
 <title>Image search</title>
 </head>
 <body>
 """
 self.footer = """
 </body>
 </html>
 """
 def index(self, query=None):
 self.src = imagesearch.Searcher('testImaAdd.db', self.voc)
 html = self.header
 html += """
 <br />
 Click an image to search. <a href='?query='> Random selection </a> of images.
 <br /><br />
 """
 if query:
 # query the database and get top images
 #查询数据库,并获取前面的图像
 res = self.src.query(query)[:self.maxres]
 for dist, ndx in res:
 imname = self.src.get_filename(ndx)
 html += "<a href='?query="+imname+"'>"
 
 html += "<img src='"+imname+"' alt='"+imname+"' width='100' height='100'/>"
 print (imname+"################")
 html += "</a>"
 # show random selection if no query
 # 如果没有查询图像则随机显示一些图像
 else:
 random.shuffle(self.ndx)
 for i in self.ndx[:self.maxres]:
 imname = self.imlist[i]
 html += "<a href='?query="+imname+"'>"
 
 html += "<img src='"+imname+"' alt='"+imname+"' width='100' height='100'/>"
 print (imname+"################")
 html += "</a>"
 html += self.footer
 return html
 index.exposed = True
#conf_path = os.path.dirname(os.path.abspath(__file__))
#conf_path = os.path.join(conf_path, "service.conf")
#cherrypy.config.update(conf_path)
#cherrypy.quickstart(SearchDemo())
cherrypy.quickstart(SearchDemo(), '/', config=os.path.join(os.path.dirname(__file__), 'service.conf'))

[global] 
server.socket_host = "127.0.0.1" 
server.socket_port = 8080 
server.thread_pool = 50 
tools.sessions.on = True 
[/] 
tools.staticdir.root = "E:/Python/pythonwatch/pcv-book-code-master/ch07" 
tools.staticdir.on = True 
tools.staticdir.dir = ""