语义识别
语义识别是什么,这个问题其实相当简答。对于人类,语义识别就是当你见到一只电老鼠,你会说出它的名字叫皮卡丘,而不是杰尼龟。我们凭借黄白相间的条纹,来识别这个会发射十万伏特的小可爱,而不是那个只会说“杰尼杰尼”的小乌龟。但是对于计算机,它不懂为什么黄白相间的条纹就是皮卡丘,而不是斑马(黑白相间??)或者是某一个生物,那它要怎么理解皮卡丘,这是一个有趣的问题。
Bag-of-words背景介绍
我们这次介绍的Bag-of-words是在语义识别方面的一个有效应用。
首先当我第一次见到这个词组我是这么理解的,有这么一个大背包,他吧所有事物的描述都集合在了包袱里,只要我能找到它的对应位置,我就能获得它的描述信息,对于我们人类(humanbeing概念的人类),这个应用显然是鸡肋的,但是对于计算机,这个只懂得01的可怜虫,这个应用可以帮它认识这个世界。从此,计算机的世界里多了一个皮卡丘。
如何理解Bag-of-words
因为刚好在学习这个概念的时候,我刚好练习了JAVA里的map应用,我觉得这两个东西的原理是极度相似的。学过JAVA的读者可能知道map是这样一个结构map<a,b>我们通过知道a,可以检索到b的位置,那么我们可以假设有这么一个映射结构,BOF<(黄色条纹,是个电耗子),皮卡丘>来检索出目标的语义为“皮卡丘”。
Bag-of-words的简单应用
原理介绍
1.生成带有sift的字典
2.利用bag-of-words进行索引
所需工具
python,service.conf
代码部分
import pickle
from PCV.imagesearch import vocabulary
from PCV.tools.imtools import get_imlist
from PCV.localdescriptors import sift
##要记得将PCV放置在对应的路径下
#获取图像列表
imlist = get_imlist('first1000/') ###要记得改成自己的路径
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
# -*- 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
##要记得将PCV放置在对应的路径下
##要记得将PCV放置在对应的路径下
#获取图像列表
imlist = get_imlist('first1000/')##记得改成自己的路径
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()
# -*- 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
##要记得将PCV放置在对应的路径下
##要记得将PCV放置在对应的路径下
# load image list and vocabulary
#载入图像列表
imlist = get_imlist('first1000/') ##要改成自己的地址
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: ##要改成自己的地址
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 thDB 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
# -*- 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'))
成果展示
tip
有时候pcv文件和python文件不在同一个文件夹下可能会出现sift生成问题。