基于BOF的图像检索

BOF

Bag of Feature (BOF)算法简介

BOF的本质是提出一种图像的特征表示方法。按照BOF算法的思想，首先我们要找到图像中的关键词，而且这些关键词必须具备较高的区分度。实际过程中，通常会采用SIFT特征。
有了特征之后，我们会将这些特征通过聚类算法得出很多聚类中心。这些聚类中心通常具有较高的代表性，比如，对于人脸来说，虽然不同人的眼睛、鼻子等特征都不尽相同，但它们往往具有共性，而这些聚类中心就代表了这类共性。我们将这些聚类中心组合在一起，形成一部字典。
对于图像中的每个「SIFT」特征，我们能够在字典中找到最相似的聚类中心，统计这些聚类中心出现的次数，可以得到一个向量表示（有些文章称之为直方图），如本文开篇的图片所示。这些向量就是所谓的Bag。这样，对于不同类别的图片，这个向量应该具有较大的区分度，基于此，我们可以训练出一些分类模型，并用其对图片进行分类。

BOF 算法过程

1、创建词汇
2、创建图像索引
3、在数据库中搜索图像

TF-IDF
对于直方图向量，我们引入 TF-IDF 权值
我们需要对每一个词给一个权重。而且这个权重必须满足以下两个条件：
1、一个词对主题预测能力越强，权重越大；
2、停止词权重为 0；

实验代码

创建数据库

from numpy import *
import pickle
import sqlite3
from functools import cmp_to_key
import operatorclass Indexer(object):def __init__(self, db, voc):""" Initialize with the name of the databaseand a vocabulary object. """self.con = sqlite3.connect(db)self.voc = vocdef __del__(self):self.con.close()def db_commit(self):self.con.commit()def get_id(self, imname):""" Get an entry id and add if not present. """cur = self.con.execute("select rowid from imlist where filename='%s'" % imname)res = cur.fetchone()if res == None:cur = self.con.execute("insert into imlist(filename) values ('%s')" % imname)return cur.lastrowidelse:return res[0]def is_indexed(self, imname):""" Returns True if imname has been indexed. """im = self.con.execute("select rowid from imlist where filename='%s'" % imname).fetchone()return im != Nonedef add_to_index(self, imname, descr):""" Take an image with feature descriptors,project on vocabulary and add to database. """if self.is_indexed(imname): returnprint('indexing', imname)# get the imidimid = self.get_id(imname)# get the wordsimwords = self.voc.project(descr)nbr_words = imwords.shape[0]# link each word to imagefor i in range(nbr_words):word = imwords[i]# wordid is the word number itselfself.con.execute("insert into imwords(imid,wordid,vocname) values (?,?,?)", (imid, word, self.voc.name))# store word histogram for image# use pickle to encode NumPy arrays as stringsself.con.execute("insert into imhistograms(imid,histogram,vocname) values (?,?,?)",(imid, pickle.dumps(imwords), self.voc.name))def create_tables(self):""" Create the database tables. """self.con.execute('create table imlist(filename)')self.con.execute('create table imwords(imid,wordid,vocname)')self.con.execute('create table imhistograms(imid,histogram,vocname)')self.con.execute('create index im_idx on imlist(filename)')self.con.execute('create index wordid_idx on imwords(wordid)')self.con.execute('create index imid_idx on imwords(imid)')self.con.execute('create index imidhist_idx on imhistograms(imid)')self.db_commit()class Searcher(object):def __init__(self, db, voc):""" Initialize with the name of the database. """self.con = sqlite3.connect(db)self.voc = vocdef __del__(self):self.con.close()def get_imhistogram(self, imname):""" Return the word histogram for an image. """im_id = self.con.execute("select rowid from imlist where filename='%s'" % imname).fetchone()s = self.con.execute("select histogram from imhistograms where rowid='%d'" % im_id).fetchone()# use pickle to decode NumPy arrays from stringreturn pickle.loads(s[0])def candidates_from_word(self, imword):""" Get list of images containing imword. """im_ids = self.con.execute("select distinct imid from imwords where wordid=%d" % imword).fetchall()return [i[0] for i in im_ids]def candidates_from_histogram(self, imwords):""" Get list of images with similar words. """# get the word idswords = imwords.nonzero()[0]# find candidatescandidates = []for word in words:c = self.candidates_from_word(word)candidates += c# take all unique words and reverse sort on occurrencetmp = [(w, candidates.count(w)) for w in set(candidates)]tmp.sort(key=cmp_to_key(lambda x, y: operator.gt(x[1], y[1])))tmp.reverse()# return sorted list, best matches firstreturn [w[0] for w in tmp]def query(self, imname):""" Find a list of matching images for imname. """h = self.get_imhistogram(imname)candidates = self.candidates_from_histogram(h)matchscores = []for imid in candidates:# get the namecand_name = self.con.execute("select filename from imlist where rowid=%d" % imid).fetchone()cand_h = self.get_imhistogram(cand_name)cand_dist = sqrt(sum(self.voc.idf * (h - cand_h) ** 2))matchscores.append((cand_dist, imid))# return a sorted list of distances and database idsmatchscores.sort()return matchscoresdef get_filename(self, imid):""" Return the filename for an image id. """s = self.con.execute("select filename from imlist where rowid='%d'" % imid).fetchone()return s[0]def tf_idf_dist(voc, v1, v2):v1 /= sum(v1)v2 /= sum(v2)return sqrt(sum(voc.idf * (v1 - v2) ** 2))def compute_ukbench_score(src, imlist):""" Returns the average number of correctimages on the top four results of queries. """nbr_images = len(imlist)pos = zeros((nbr_images, 4))# get first four results for each imagefor i in range(nbr_images):pos[i] = [w[1] - 1 for w in src.query(imlist[i])[:4]]# compute score and return averagescore = array([(pos[i] // 4) == (i // 4) for i in range(nbr_images)]) * 1.0return sum(score) / (nbr_images)# import PIL and pylab for plotting
from PIL import Image
from pylab import *def plot_results(src, res):""" Show images in result list 'res'. """figure()nbr_results = len(res)for i in range(nbr_results):imname = src.get_filename(res[i])subplot(1, nbr_results, i + 1)imshow(array(Image.open(imname)))axis('off')show()

搜索图像

# -*- 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('E:/test_pic/BOF/')
nbr_images = len(imlist)
#获取特征列表
featlist = [imlist[i][:-3]+'sift' for i in range(nbr_images)]#载入词汇
f = open('E:/test_pic/BOF/vocabulary.pkl', 'rb')
voc = pickle.load(f)
f.close()src = imagesearch.Searcher('testImaAdd.db',voc)
locs,descr = sift.read_features_from_file(featlist[0])
iw = voc.project(descr)print ('ask using a histogram...')
print (src.candidates_from_histogram(iw)[:5])src = imagesearch.Searcher('testImaAdd.db',voc)
print ('try a query...')
print(src.query(imlist[0])[:5])nbr_results = 5
res = [w[1] for w in src.query(imlist[0])[:nbr_results]]
imagesearch.plot_results(src,res)

实验结果

输入图片：

得到结果：

结果分析
可以看出，得出的结果是有一定的相似度的。
不选去有文字的图片尽心检索应该会使结果更好一些。数据集中也最好不要出现文字图片，我的数据集是表情包，所以难免会有文字在其中。
在图像特征比较明显，或者数据集中图片相似的很多，则图像的匹配效果越好
BOF算法还有一个明显的不足，就是它完全没有考虑到特征之间的位置关系，而位置信息对于人理解图片来说，作用是很明显的。
而且在提取特征时不需要相关的 label 进行学习，因此是一种弱监督的学习方法。