图像识别与搜索
一丶实验原理
Bag of words算法
Bagofwords模型,也叫做“词袋”,在信息检索中,Bag of words model假定对于一个文本,忽略其词序和语法、句法,将其仅仅看做是一个词集合,或者说是词的一个组合,文本中每个词的出现都是独立的,不依赖于其他词是否出现,或者说当这篇文章的作者在任意一个位置选择一个词汇都不受前面句子的影响而独立选择的。
二丶实验代码
生成词汇表
import pickle
from PCV.imagesearch import vocabulary
from PCV.tools.imtools import get_imlist
from PCV.localdescriptors import sift
from PCV.imagesearch import imagesearch
from PCV.geometry import homography
from sqlite3 import dbapi2 as sqlite
#获取图像列表
imlist = get_imlist('datasets/')
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, 888, 10) # 使用k-means算法在featurelist里边训练处一个词汇
# 注意这里使用了下采样的操作加快训练速度
# 将描述子投影到词汇上,以便创建直方图
#保存词汇
# saving vocabulary
with open('BOW/vocabulary.pkl', 'wb') as f:
pickle.dump(voc, f)
print ('vocabulary is:', voc.name, voc.nbr_words)
生成数据库
import pickle
from PCV.imagesearch import vocabulary
from PCV.tools.imtools import get_imlist
from PCV.localdescriptors import sift
from PCV.imagesearch import imagesearch
from PCV.geometry import homography
from sqlite3 import dbapi2 as sqlite # 使用sqlite作为数据库
#获取图像列表
imlist = get_imlist('datasets/')
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('BOW/vocabulary.pkl', 'rb') as f:
voc = pickle.load(f)
#创建索引
indx = imagesearch.Indexer('testImaAdd.db',voc) # 在Indexer这个类中创建表、索引,将图像数据写入数据库
indx.create_tables() # 创建表
# 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)[:888]:
locs,descr = sift.read_features_from_file(featlist[i])
indx.add_to_index(imlist[i],descr) # 使用add_to_index获取带有特征描述子的图像,投影到词汇上
# 将图像的单词直方图编码存储
# 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())
图像搜索
# -*- coding: utf-8 -*-
#使用视觉单词表示图像时不包含图像特征的位置信息
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('E:/Python37_course/test7/first1000/')
imlist = get_imlist('datasets/')
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('E:/Python37_course/test7/first1000/vocabulary.pkl', 'rb') as f:
voc = pickle.load(f)'''
with open('BOW/vocabulary.pkl', 'rb') as f:
voc = pickle.load(f)
src = imagesearch.Searcher('testImaAdd.db',voc)# Searcher类读入图像的单词直方图执行查询
# 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 = 130
# 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]] # 查询的结果
print ('top matches (regular):', res_reg)
# load image features for query image
#载入查询图像特征进行匹配
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:]:
try:
locs,descr = sift.read_features_from_file(featlist[ndx])
except:
continue
#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
# 计算单应性矩阵
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
# 对字典进行排序,可以得到重排之后的查询结果
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[:6]) #常规查询
imagesearch.plot_results(src,res_geom[:6]) #重排后的结果
三丶实验结果
图片数据库部分图片
实验结果
实验分析
两次图片的匹配结果都与原图不符。匹配的图片部分与结果图片相符所以得出了结果,但由于算法原因得出的结果与原图相差较大。