python基于内容的图像检索（CBIR)
开始之前首先要安装几个python第三方库包：pyQt5、cherrypy、pysqlite(我是python3.7安装的pysqlite3）
将PCV文件包及vlfeat放到工作目录下，配置sift文件
一、原理介绍：
基于内容的图像检索(CBIR)是指根据图像颜色、纹理、形状等视觉特征，在给定的图像库中查找含有一定特征的图像。它融合了图像理解技术，在输入图像的同时将其相应的特征向量也存入特征库。在进行图像检索时，对每-幅给定的关键图，进行图像分析，并提取图像的特征向量。将该图像的特征向量和特征库中的特征向量进行匹配，根据相似距离的大小在图像库中进行搜索就可以得到所需要的检索图了。其关键技术在于图像特征提取和特征匹配。
二、方法分类：
1、基于 SIFT 特征方法（本文采用）
2、基于 CNN 的方法
三、基本步骤：
1.建立图像数据库
2.对输入的图像进行分析并分类统一建模
3.根据各种图像模型提取图像特征存入特征库， 同时对特征库建立索引
4.根据条件查询测试图片
四、代码实现：
1.添加图片
# -*- 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())
2.创建词汇
# -*- 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)
3.图像索引
# -*- 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
4.模型
# -*- 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 = """
Image search
"""
self.footer = """