基于BOW图像检索python实现

代码地址：https://pan.baidu.com/s/1X2Ykoi8j3_6f6qTvhh95jw

准备：

1. vlfeat（SIFT的开源实现）
2. 安装sqlite-web：pip install sqlite-web(好像没有用到，python3有自带的sqlite3)
3. 安装cherryPy（轻量级网页服务器）：pip install cherrypy
4. 图片库：First1000

流程

• 用vlfeat（SIFT特征模型）提取每一张图片的特征点
• 将每一张图的特征点采样聚类成图片的视觉单词
• 即视觉单词，就是对应图片的代表
• 创建数据库，将每张图片的视觉单词入库，并建立索引
• 编写cherryPy的web应用，根据点击的图片搜索相似的图片

提取图片特征点并生成单词文件

 

# -*- 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)

将图片单词信息存进数据库

# -*- 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())

执行后会生成：

测试：

将数据放进数据库中之后就可以开始测试我们的图片索引。

# -*- 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

配置cherryPy网页应用

• 每点击图片时随机显示10张图片
• 点击其中一张图片，搜索相似的图片显示出来
• 本质是根据点击图片的单词，寻找在数据库中与之相近的单词，并将其显示出来
• 浏览地址： http://127.0.0.1:8080

# -*- 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'))

结果：

不搜索时：

点击搜索第二幅图时：

 从相似图像的搜索结果可以 看出基于BOW的搜索效果还是较为准确的，但是还存在一定的误差；例如第三副图搜索的是与树有关的图像结果却搜索到了花。