当前位置： 首页 > news >正文

[Computer Vision]实验七：图像检索

news 来源：原创 2025/5/1 9:23:35

目录

一、实验内容

二、实验过程

2.1 准备数据集

2.2 SIFT特征提取

2.3 学习“视觉词典”（vision vocabulary）

2.4 建立图像索引并保存到数据库中

2.5 用一幅图像查询

三、实验小结

一、实验内容

  1. 实现基于颜色直方图、bag of word等方法的以图搜图，打印图片特征向量、图片相似度等
  2. 打印视觉词典大小、可视化部分特征基元、可视化部分图片的频率直方图

二、实验过程

2.1 准备数据集

如图1所示，这里准备的文件夹中含有100张实验图片。

图1
2.2 SIFT特征提取

2.2.1 实验代码

import os
import cv2
import numpy as np
from PCV.tools.imtools import get_imlist
#获取图像列表
imlist = get_imlist(r'D:\Computer vision\20241217dataset')
nbr_images = len(imlist)
#生成特征文件路径
featlist = [os.path.splitext(imlist[i])[0] + '.sift' for i in range(nbr_images)]
#创建sift对象
sift = cv2.SIFT_create()
#提取sift特征并保存
for i in range(nbr_images):
    try:
        img = cv2.imread(imlist[i], cv2.IMREAD_GRAYSCALE)
        if img is None:
            raise ValueError(f"Image {imlist[i]} could not be read")
        
        keypoints, descriptors = sift.detectAndCompute(img, None)
        
        locs = np.array([[kp.pt[0], kp.pt[1], kp.size, kp.angle] for kp in keypoints])
        np.savetxt(featlist[i], np.hstack((locs, descriptors)))
        print(f"Processed {imlist[i]} to {featlist[i]}")
    except Exception as e:
        print(f"Failed to process {imlist[i]}: {e}")
#可视化sift特征
def visualize_sift_features(image_path, feature_path):
    img = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
    if img is None:
        raise ValueError(f"Image {image_path} could not be read")
    
    features = np.loadtxt(feature_path)
    locs = features[:, :4]
    descriptors = features[:, 4:]
    
    img_with_keypoints = cv2.drawKeypoints(img, [cv2.KeyPoint(x=loc[0], y=loc[1], _size=loc[2], _angle=loc[3]) for loc in locs], outImage=np.array([]))
    
    plt.figure(figsize=(10, 10))
    plt.imshow(img_with_keypoints, cmap='gray')
    plt.title('SIFT Features Visualization')
    plt.axis('off')
    plt.show()

visualize_sift_features(imlist[0], featlist[0])

2.2.2 结果展示

 如图2所示，对文件夹中的所有图片使用sift特征描述子，图3展示了对第一个图像的SIFT特征的可视化。

图2
图3
2.3 学习“视觉词典”（vision vocabulary）

2.3.1 实验代码

（1）vocabulary.py文件

from numpy import *
from scipy.cluster.vq import *
from PCV.localdescriptors import sift
#构建视觉词汇表
class Vocabulary(object):
  #初始化方法
    def __init__(self,name):
        self.name = name
        self.voc = []
        self.idf = []
        self.trainingdata = []
        self.nbr_words = 0
    #训练过程
    def train(self,featurefiles,k=100,subsampling=10):
        nbr_images = len(featurefiles)

        descr = []
        descr.append(sift.read_features_from_file(featurefiles[0])[1])
        descriptors = descr[0] 
        for i in arange(1,nbr_images):
            descr.append(sift.read_features_from_file(featurefiles[i])[1])
            descriptors = vstack((descriptors,descr[i]))
            #使用K-means聚类生成视觉单词
        self.voc,distortion = kmeans(descriptors[::subsampling,:],k,1)
        self.nbr_words = self.voc.shape[0]
        #生成视觉单词的直方图
        imwords = zeros((nbr_images,self.nbr_words))
        for i in range( nbr_images ):
            imwords[i] = self.project(descr[i])
        
        nbr_occurences = sum( (imwords > 0)*1 ,axis=0)
        #计算每个视觉单词的逆文档频率
        self.idf = log( (1.0*nbr_images) / (1.0*nbr_occurences+1) )
        self.trainingdata = featurefiles
    #投影方法
    def project(self,descriptors):
        
        imhist = zeros((self.nbr_words))
        words,distance = vq(descriptors,self.voc)
        for w in words:
            imhist[w] += 1
        
        return imhist
    
    def get_words(self,descriptors):
        return vq(descriptors,self.voc)[0]

（2）visual vocabulary.py文件

import pickle
from PCV.imagesearch import vocabulary
from PCV.tools.imtools import get_imlist

imlist = get_imlist(r'D:\Computer vision\20241217dataset')
nbr_images = len(imlist)

featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]
voc = vocabulary.Vocabulary('bof_test')
voc.train(featlist, 50, 10)
 
with open(r'D:\Computer vision\20241217dataset\vocabulary50.pkl', 'wb') as f:
    pickle.dump(voc, f)
print('vocabulary is:', voc.name, voc.nbr_words)

2.3.2 结果展示

 如图4所示，打印视觉词典的名称和长度

图4
2.4 建立图像索引并保存到数据库中

2.4.1 实验代码

（1）imagesearch.py文件

from numpy import *
import pickle
import sqlite3 as sqlite
from functools import cmp_to_key

class Indexer(object):
    
    def __init__(self,db,voc):
        self.con = sqlite.connect(db)
        self.voc = voc
    
    def __del__(self):
        self.con.close()
    
    def db_commit(self):
        self.con.commit()
    
    def get_id(self,imname):
        
        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.lastrowid
        else:
            return res[0] 
    
    def is_indexed(self,imname):
        
        im = self.con.execute("select rowid from imlist where filename='%s'" % imname).fetchone()
        return im != None
    
def add_to_index(self,imname,descr):
            
        if self.is_indexed(imname): return
        print ('indexing', imname)
        
        imid = self.get_id(imname)
        
        imwords = self.voc.project(descr)
        nbr_words = imwords.shape[0]
        
        for i in range(nbr_words):
            word = imwords[i]
            self.con.execute("insert into imwords(imid,wordid,vocname) values (?,?,?)", (imid,word,self.voc.name))
            
        self.con.execute("insert into imhistograms(imid,histogram,vocname) values (?,?,?)", (imid,pickle.dumps(imwords),self.voc.name))
    
    def create_tables(self): 
        
        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()

def cmp_for_py3(a, b):
    return (a > b) - (a < b)

class Searcher(object):
    
    def __init__(self,db,voc):
        self.con = sqlite.connect(db)
        self.voc = voc
    
    def __del__(self):
        self.con.close()
    def get_imhistogram(self, imname):
        cursor = self.con.execute(
            "select rowid from imlist where filename='%s'" % imname)
        row = cursor.fetchone()
        if row is None:
            raise ValueError(f"No entry found in imlist for filename: {imname}")
        im_id = row[0]
        cursor = self.con.execute(
            "select histogram from imhistograms where rowid=%d" % im_id)
        s = cursor.fetchone()
        if s is None:
            raise ValueError(f"No histogram found for rowid: {im_id}")
        return pickle.loads(s[0])

    def candidates_from_word(self,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):
        
        words = imwords.nonzero()[0]
        
        candidates = []
        for word in words:
            c = self.candidates_from_word(word)
            candidates+=c
        
        tmp = [(w,candidates.count(w)) for w in set(candidates)]
        tmp.sort(key=cmp_to_key(lambda x,y:cmp_for_py3(x[1],y[1])))
        tmp.reverse()
        
        return [w[0] for w in tmp] 
    
    def query(self, imname):
        try:
            h = self.get_imhistogram(imname)
        except ValueError as e:
            print(e)
            return []
        
        candidates = self.candidates_from_histogram(h)
        matchscores = []
        for imid in candidates:
            cand_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))
        matchscores.sort()
        return matchscores
    
    def get_filename(self,imid):
        
        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):
        
    nbr_images = len(imlist)
    pos = zeros((nbr_images,4))
    for i in range(nbr_images):
        pos[i] = [w[1]-1 for w in src.query(imlist[i])[:4]]
    
    score = array([ (pos[i]//4)==(i//4) for i in range(nbr_images)])*1.0
    return sum(score) / (nbr_images)

from PIL import Image
from pylab import *

def plot_results(src,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()

（2）quantizeSet.py文件

import pickle
from PCV.imagesearch import imagesearch
from PCV.localdescriptors import sift
import sqlite3
from PCV.tools.imtools import get_imlist
import cv2
import matplotlib.pyplot as plt
 
imlist = get_imlist(r'D:\Computer vision\20241217dataset')
nbr_images = len(imlist)

featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]
 
with open(r'D:\Computer vision\20241217dataset\vocabulary50.pkl', 'rb') as f:
    voc = pickle.load(f)
indx = imagesearch.Indexer('D:\\Computer vision\\20241217CODES\\testImaAdd.db', voc)
indx.create_tables()
for i in range(nbr_images)[:100]:
    locs, descr = sift.read_features_from_file(featlist[i])
    indx.add_to_index(imlist[i], descr)
indx.db_commit()
con = sqlite3.connect('D:\\Computer vision\\20241217CODES\\testImaAdd.db')
print(con.execute('select count (filename) from imlist').fetchone())
print(con.execute('select * from imlist').fetchone())
searcher = imagesearch.Searcher('D:\\Computer vision\\20241217CODES\\testImaAdd.db', voc)

image_files = imlist[:5]

for image_file in image_files:
    histogram = searcher.get_imhistogram(image_file)
    plt.figure()
    plt.title(image_file)
    plt.bar(range(len(histogram)), histogram)
    plt.xlabel('Word ID')
    plt.ylabel('Frequency')
    plt.show()

2.4.2 结果展示

如图5所示，对数据集中的所有图像进行量化，为所有图像创建索引，再遍历所有的图像，将它们的特征投影到词汇上，最终提交到数据库保存下来（如图6）。图7、图8展示了部分图像的频率直方图。

图5
图6
图7
图8
2.5 用一幅图像查询

2.5.1 实验代码

import pickle
from PCV.imagesearch import imagesearch
from PCV.geometry import homography
from PCV.tools.imtools import get_imlist
import numpy as np
import cv2
import warnings
warnings.filterwarnings("ignore")

imlist = get_imlist(r'D:\Computer vision\20241217dataset')
nbr_images = len(imlist)
featlist = [imlist[i][:-3] + 'sift' for i in range(nbr_images)]

with open(r'D:\Computer vision\20241217dataset\vocabulary50.pkl', 'rb') as f:
    voc = pickle.load(f, encoding='iso-8859-1')

src = imagesearch.Searcher(r'D:\Computer vision\20241217CODES\testImaAdd.db', voc)

q_ind = 3
nbr_results = 10

res_reg = [w[1] for w in src.query(imlist[q_ind])[:nbr_results]] 
print('top matches (regular):', res_reg)

img = cv2.imread(imlist[q_ind])
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
sift = cv2.SIFT_create()
kp, q_descr = sift.detectAndCompute(gray, None)
q_locs = np.array([[kp[i].pt[0], kp[i].pt[1]] for i in range(len(kp))])
fp = homography.make_homog(q_locs[:, :2].T)

model = homography.RansacModel()
rank = {}

bf = cv2.BFMatcher() 
for ndx in res_reg[1:]:
    if ndx >= len(imlist):
        print(f"Index {ndx} is out of range for imlist with length {len(imlist)}")
        continue
    img = cv2.imread(imlist[ndx])
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    kp, descr = sift.detectAndCompute(gray, None)
    locs = np.array([[kp[i].pt[0], kp[i].pt[1]] for i in range(len(kp))])
    matches = bf.knnMatch(q_descr, descr, k=2)
    good_matches = []
    for m, n in matches:
        if m.distance < 0.75 * n.distance:
            good_matches.append(m)
    ind = [m.queryIdx for m in good_matches]
    ind2 = [m.trainIdx for m in good_matches]
    tp = homography.make_homog(locs[:, :2].T)
    try:
        H, inliers = homography.H_from_ransac(fp[:, ind], tp[:, ind2], model, match_theshold=4)
    except:
        inliers = []
    # store inlier count
    rank[ndx] = len(inliers)

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)

def calculate_similarity(query_index, result_indices, imlist):
    similarities = []
    for res_index in result_indices:
        if res_index >= len(imlist):
            print(f"Index {res_index} is out of range for imlist with length {len(imlist)}")
            continue
        img1 = cv2.imread(imlist[query_index])
        img2 = cv2.imread(imlist[res_index])
        gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
        gray2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
        sift = cv2.SIFT_create()
        kp1, des1 = sift.detectAndCompute(gray1, None)
        kp2, des2 = sift.detectAndCompute(gray2, None)
        bf = cv2.BFMatcher()
        matches = bf.knnMatch(des1, des2, k=2)
        good_matches = []
        for m, n in matches:
            if m.distance < 0.75 * n.distance:
                good_matches.append(m)
        similarity = len(good_matches) / min(len(kp1), len(kp2))
        similarities.append((res_index, similarity))
    return similarities

query_index = q_ind
result_indices = res_reg + res_geom
similarities = calculate_similarity(query_index, result_indices, imlist)

print("Similarity scores:")
for index, score in similarities:
    print(f"Image {index}: {score:.4f}")

imagesearch.plot_results(src, res_reg)
imagesearch.plot_results(src, res_geom)
imagesearch.plot_results(src, res_reg[:6])
imagesearch.plot_results(src, res_geom[:6])  

2.5.2  结果展示

如图9所示，根据给定的查询图像索引q_ind，执行常规查询，返回前nbr_results个匹配结果，并打印这些结果以及可视化图片。

图 9 维度=50（常规排序）

如图10所示，使用 RANSAC 模型拟合单应性找到与查询图像几何一致的候选图像。

图 10 维度=50（重排序）

 如图11所示，计算查询图像与候选图像之间的相似度分数，并返回一个包含相似度分数的列表。

图11

当生成不同维度视觉词典时，常规排序结果如图12所示。

图 12 维度=10（常规排序）

三、实验小结

图像检索是一项重要的计算机视觉任务，它在根据用户的输入（如图像或关键词），从图像数据库中检索出最相关的图像。Bag of Feature 是一种图像特征提取方法，参考Bag of Words的思路，把每幅图像描述为一个局部区域/关键点(Patches/Key Points)特征的无序集合。同时从图像抽象出很多具有代表性的「关键词」，形成一个字典，再统计每张图片中出现的「关键词」数量，得到图片的特征向量。

相关文章：

  • 摄像头应用编程（四）：ARM Linux LCD实时预览UVC摄像头画面
  • 摄像头应用编程（三）：多平面视频采集
  • 009---基于Verilog HDL的单比特信号边沿检测
  • 【前端】在WebStorm中安装Node.js与nvm与npm的详细过程
  • 第15届 蓝桥杯 C++编程青少组中级省赛 202408 真题答案及解析
  • 从新加坡《Companion Guide on Securing AI Systems 》看可信AI全生命周期防护框架构建
  • SOUI基于Zint生成EAN码
  • QT-信号与槽
  • deepseek、腾讯元宝deepseek R1、百度deepseekR1关系
  • 【自学笔记】Spring基础知识点总览-持续更新
  • Java的异常体系中的Error
  • 如何在网页上显示3D CAD PMI
  • Grok 3能否打破大模型的魔咒？
  • 【四.RAG技术与应用】【1.RAG技术揭秘：大模型与检索增强生成】
  • Error Density-dependent Empirical Risk Minimization
  • 基于IMM算法的目标跟踪，四模型IMM|三维环境|4个模型分别是：CV、左转CT、右转CT、CA（基于EKF，订阅专栏后可获得完整源代码）
  • 计算机视觉之dlib人脸关键点绘制及微笑测试
  • VMware虚拟机IP配置
  • GCC RISCV 后端 -- GCC 构建系统简介
  • 《2025软件测试工程师面试》功能测试篇
  • 美乌矿产协议预计最早于今日签署
  • 大型长读长RNA测序数据集发布，有助制定精准诊疗策略
  • 贵州茅台一季度净利268亿元增长11.56%，系列酒营收增近两成
  • 五一“拼假”催热超长假期，热门酒店民宿一房难求
  • 成都警方：在地铁公共区域用改装设备偷拍女乘客，男子被行拘
  • 船只深夜撞上海上风机后沉没1死1失踪，调查报告公布