当前位置： 首页 > news >正文

网站悬浮窗广告/网上怎么做推广

news 2025/8/7 11:31:10
网站悬浮窗广告,网上怎么做推广,电影网站做cpa,武汉网站建设的公司通过提取特征进行图像的匹配与搜索 1 特征检测算法 常见的特征和提取算法: Harris 检测角点 Sift 检测斑点(blob) 有专利保护 Surf 检测斑点 有专利保护 Fast 检测角点 Brief 检测斑点 Orb 带方向的fast算法和具有旋转不变性的brief算法 特征的定义 #!/usr/bin/env …

 

通过提取特征进行图像的匹配与搜索

 

1 特征检测算法

常见的特征和提取算法:

Harris 检测角点

Sift 检测斑点(blob) 有专利保护

Surf 检测斑点   有专利保护

Fast 检测角点

Brief 检测斑点

Orb  带方向的fast算法和具有旋转不变性的brief算法

 

特征的定义

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/5 12:30
# @Author  : Retacn
# @Site    : 检测图像的角点
# @File    : cornerHarris.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"import cv2
import numpy as np# 读入图像
img = cv2.imread('../test1.jpg')
# 转换颜色空间
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = np.float32(gray)
# 检测图像角点
dst = cv2.cornerHarris(gray,2,23,  # sobel算子的中孔,3-31之间的奇数0.04)
# 将检测到有角点标记为红色
img[dst > 0.01 * dst.max()] = [0, 0, 255]
while (True):cv2.imshow("corners", img)if cv2.waitKey(33) & 0xFF == ord('q'):break
cv2.destroyAllWindows()

 

 

使用dog和sift进行特征提取和描述

示例代码如下:

import cv2
import sys
import numpy as py# 读入图像
# imgpath=sys.argv[1]
imgpath = '../test1.jpg'
img = cv2.imread(imgpath)
# 更换颜色空间
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 创建sift对象,计算灰度图像,会使用dog检测角点
sift = cv2.xfeatures2d.SIFT_create()
keypoints, descriptor = sift.detectAndCompute(gray, None)# print(keypoints)
# 关键点有以下几个属性
# angle 表示特征的方向
# class_id 关键点的id
# octave 特征所在金字塔的等级
# pt 图像中关键点的坐标
# response 表示关键点的强度
# size  表示特征的直径
img = cv2.drawKeypoints(image=img,outImage=img,keypoints=keypoints,color=(51, 163, 236),flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)# 显示图像
cv2.imshow('sift_keypoints', img)
while (True):if cv2.waitKey(int(1000 / 12)) & 0xFF == ord('q'):break
cv2.destroyAllWindows()

 

使用心有快速hessian算法和SURF来提取特征

示例代码发如下:

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/10 17:30
# @Author  : Retacn
# @Site    : sift用于检测斑点
# @File    : sift.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"import cv2
import sys
import numpy as py# 读入图像
# imgpath=sys.argv[1]
# alg=sys.argv[2]
# threshold=sys.argv[3]imgpath = '../test1.jpg'
img = cv2.imread(imgpath)
# alg = 'SURF'
alg = 'SIFT'
# threshold = '8000'
# 阈值越小特征点越多
threshold = '4000'def fd(algorithm):if algorithm == 'SIFT':return cv2.xfeatures2d.SIFT_create()if algorithm == 'SURF':# return cv2.xfeatures2d.SURF_create(float(threshold) if len(sys.argv) == 4 else 4000)return cv2.xfeatures2d.SURF_create(float(threshold))# 更换颜色空间
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 创建sift对象,计算灰度图像,会使用dog检测角点
fd_alg = fd(alg)
keypoints, descriptor = fd_alg.detectAndCompute(gray, None)# print(keypoints)
# 关键点有以下几个属性
# angle 表示特征的方向
# class_id 关键点的id
# octave 特征所在金字塔的等级
# pt 图像中关键点的坐标
# response 表示关键点的强度
# size  表示特征的直径
img = cv2.drawKeypoints(image=img,outImage=img,keypoints=keypoints,color=(51, 163, 236),flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)# 显示图像
cv2.imshow('keypoints', img)
while (True):if cv2.waitKey(int(1000 / 12)) & 0xFF == ord('q'):break
cv2.destroyAllWindows()

 

基于ORB的特征检测和特征匹配

ORB是基于

FAST(featuresfrom accelerated segment test)关键点检测技术

在像素周围绘制一个圆,包含16个像素

BRIEF(binaryrobust independent elementary features) 描述符

 

 

暴力（brute-force）匹配法

比较两个描述符,并产生匹配结果

 

ORB特征匹配

示例代码如下:

import numpy as np
import cv2
from matplotlib import pyplot as pltcv2.ocl.setUseOpenCL(False)
# 读入灰度图像
img1 = cv2.imread('../test2_part.jpg', cv2.IMREAD_GRAYSCALE)
img2 = cv2.imread('../test2.jpg', cv2.IMREAD_GRAYSCALE)# 创建orb特征检测器和描述符
orb = cv2.ORB_create()
kp1, des1 = orb.detectAndCompute(img1, None)
kp2, des2 = orb.detectAndCompute(img2, None)# 暴力匹配
bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)
matches = bf.match(des1, des2)
matches = sorted(matches, key=lambda x: x.distance)# 显示图像
img3 = cv2.drawMatches(img1, kp1, img2, kp2, matches[:40], img2, flags=2)
plt.imshow(img3), plt.show()

 

 

 

 

 

 

 

报如下错误:

cv2.error: D:\Build\OpenCV\opencv-3.1.0\modules\python\src2\cv2.cpp:163:error: (-215) The data should normally be NULL! in functionNumpyAllocator::allocate

解决办法,添加如下代码 :

 cv2.ocl.setUseOpenCL(False)

 

k最邻近配匹

import numpy as np
import cv2
from matplotlib import pyplot as pltcv2.ocl.setUseOpenCL(False)
# 读入灰度图像
img1 = cv2.imread('../test2_part.jpg', cv2.IMREAD_GRAYSCALE)
img2 = cv2.imread('../test2.jpg', cv2.IMREAD_GRAYSCALE)# 创建orb特征检测器和描述符
orb = cv2.ORB_create()
kp1, des1 = orb.detectAndCompute(img1, None)
kp2, des2 = orb.detectAndCompute(img2, None)# knn匹配,返回k个匹配
bf = cv2.BFMatcher(cv2.NORM_L1, crossCheck=False)
matches = bf.knnMatch(des1, des2, k=2)# 显示图像
img3 = cv2.drawMatchesKnn(img1, kp1, img2, kp2, matches, img2, flags=2)
plt.imshow(img3), plt.show()

 

 

 

 

Flann匹配法

Fast library for approximate nearestneighbors  近似最近邻的快速库

import numpy as np
import cv2
from matplotlib import pyplot as plt# 读入图像
queryImage = cv2.imread('../test2_part.jpg', cv2.IMREAD_GRAYSCALE)
trainingImage = cv2.imread('../test2.jpg', cv2.IMREAD_GRAYSCALE)# 创建sift对象
sift = cv2.xfeatures2d.SIFT_create()
kp1, des1 = sift.detectAndCompute(queryImage, None)
kp2, des2 = sift.detectAndCompute(trainingImage, None)FLANN_INDEX_KDTREE = 0
# 创建字典参数
indexParams = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)  # 处理索引
searchParams = dict(checks=50)  # 创建对象,用来指定索引树的遍历次数flann = cv2.FlannBasedMatcher(indexParams, searchParams)matches = flann.knnMatch(des1, des2, k=2)matchesMask = [[0, 0] for i in range(len(matches))]for i, (m, n) in enumerate(matches):if m.distance < 0.7 * n.distance:matchesMask[i] = [1, 0]
drawParams = dict(matchColor=(0, 255, 0),singlePointColor=(255, 0, 0),matchesMask=matchesMask,flags=0)resultImage = cv2.drawMatchesKnn(queryImage, kp1, trainingImage, kp2, matches, None, **drawParams)
plt.imshow(resultImage), plt.show()

 

 

运行结果如下:

 

 

Flann单应性匹配

 

示例代码如下:

 

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/11 12:02
# @Author  : Retacn
# @Site    : flann的单应性匹配
# @File    : flann_homography.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"import numpy as np
import cv2
from matplotlib import pyplot as pltMIN_MATCH_COUNT = 10# 读入图像
img1 = cv2.imread('../test3_part.jpg', cv2.IMREAD_GRAYSCALE)
img2 = cv2.imread('../test3.jpg', cv2.IMREAD_GRAYSCALE)# 创建sift对象
sift = cv2.xfeatures2d.SIFT_create()
# 查询特征点和描述符
kp1, des1 = sift.detectAndCompute(img1, None)
kp2, des2 = sift.detectAndCompute(img2, None)FLANN_INDEX_KDTREE = 0
# 创建字典参数
indexParams = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)  # 处理索引
searchParams = dict(checks=50)  # 创建对象,用来指定索引树的遍历次数flann = cv2.FlannBasedMatcher(indexParams, searchParams)matches = flann.knnMatch(des1, des2, k=2)good = []
for m, n in matches:if m.distance < 0.7 * n.distance:good.append(m)if len(good) > MIN_MATCH_COUNT:# 在原始图像和训练图像中查询特征点src_pts = np.float32([kp1[m.queryIdx].pt for m in good]).reshape(-1, 1, 2)dst_pts = np.float32([kp2[m.trainIdx].pt for m in good]).reshape(-1, 1, 2)# 单应性M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)matchesMask = mask.ravel().tolist()# 对第二张图片计算相对于原始图像的投影畸变,并绘制边框h, w = img1.shapepts = np.float32([[0, 0], [0, h - 1], [w - 1, h - 1], [w - 1, 0]]).reshape(-1, 1, 2)dst = cv2.perspectiveTransform(pts, M)img2 = cv2.polylines(img2, [np.int32(dst)], True, 255, 3, cv2.LINE_AA)
else:print("Not enough matches are found -%d/%d" % (len(good), MIN_MATCH_COUNT))matchesMask = None# 显示图像
draw_params = dict(matchColor=(0, 255, 0),  # 绿线singlePointColor=None,matchesMask=matchesMask,flags=2)
img3 = cv2.drawMatches(img1, kp1, img2, kp2, good, None, **draw_params)
plt.imshow(img3, 'gray'), plt.show()

 

运行结果如下:

 

 

 

 

 

基于纹身取证的应用程序示例

A 将图像描述符保存到文件中

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/11 13:52
# @Author  : Retacn
# @Site    : 将图像描述符保存到文件中
# @File    : generate_descriptors.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"import cv2
import numpy as np
from os import walk
from os.path import join
import sys# 创建描述符
def create_descriptors(folder):files = []for (dirpath, dirnames, filenames) in walk(folder):files.extend(filenames)for f in files:save_descriptor(folder, f, cv2.xfeatures2d.SIFT_create())# 保存描述符
def save_descriptor(folder, image_path, feature_detector):print("reading %s" % image_path)if image_path.endswith("npy") or image_path.endswith("avi"):returnimg = cv2.imread(join(folder, image_path), cv2.IMREAD_GRAYSCALE)keypoints, descriptors = feature_detector.detectAndCompute(img, None)descriptor_file = image_path.replace("jpg", "npy")np.save(join(folder, descriptor_file), descriptors)# 从执行参数中取得文件目录
dir = sys.argv[1]
create_descriptors(dir)

 

 

 

B 扫描匹配

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2016/12/11 14:05
# @Author  : Retacn
# @Site    : 扫描匹配
# @File    : scan4matches.py
# @Software: PyCharm
__author__ = "retacn"
__copyright__ = "property of mankind."
__license__ = "CN"
__version__ = "0.0.1"
__maintainer__ = "retacn"
__email__ = "zhenhuayue@sina.com"
__status__ = "Development"from os.path import join
from os import walk
import numpy as np
import cv2
from sys import argv
from matplotlib import pyplot as plt# 创建文件名数组
folder = argv[1]
query = cv2.imread(join(folder, 'part.jpg'), cv2.IMREAD_GRAYSCALE)# 创建全局的文件,图片,描述符
files = []
images = []
descriptors = []
for (dirpath, dirnames, filenames) in walk(folder):files.extend(filenames)for f in files:if f.endswith('npy') and f != 'part.npy':descriptors.append(f)print(descriptors)# 创建sift检测器
sift = cv2.xfeatures2d.SIFT_create()
query_kp, query_ds = sift.detectAndCompute(query, None)# 创建flann匹配
FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
flann = cv2.FlannBasedMatcher(index_params, search_params)# 最小匹配数
MIN_MATCH_COUNT = 10potential_culprits = {}
print(">> Initiating picture scan...")
for d in descriptors:print("--------- analyzing %s for matches ------------" % d)matches = flann.knnMatch(query_ds, np.load(join(folder, d)), k=2)good = []for m, n in matches:if m.distance < 0.7 * n.distance:good.append(m)if len(good) > MIN_MATCH_COUNT:print('%s is a match! (%d)' % (d, len(good)))else:print('%s is not a match ' % d)potential_culprits[d] = len(good)max_matches = None
potential_suspect = None
for culprit, matches in potential_culprits.items():if max_matches == None or matches > max_matches:max_matches = matchespotential_suspect = culprit
print("potential suspect is %s" % potential_suspect.replace("npy", "").upper())

 

http://www.lbrq.cn/news/1057609.html

相关文章：

  • 网站建设冫首先金手指十五/厉害的seo顾问
  • 主机搭建网站教程/视频号链接怎么获取
  • 影楼网站推广/seo五大经验分享
  • 企业网站模块介绍/如何做网站推广及优化
  • 我做微信淘宝客网站/优秀软文案例
  • 做网站加手机app需要多少钱/百度pc端入口
  • 南京定制网站建设公司/网站推广要点
  • 定制制作网站公司/个人网站模板
  • 十大赚钱小程序/seo牛人
  • php网站源码/杭州优化公司哪家好
  • 常用网站png/网上商城推广13种方法
  • 用asp怎么做网站/网络营销软件排行
  • 中国建设银行辽宁分行网站/首页排名优化公司
  • 哪个网站可以做英文兼职/网络营销到底是干嘛的
  • 河北省住房与建设厅网站/新站整站优化
  • 莱西做网站公司/搜索引擎营销的英文缩写是
  • 网站的建设要多少钱/网页做推广
  • wordpress have posts/佛山做网络优化的公司
  • wordpress hotnews/武汉本地seo
  • 沈阳企业定制网站建设/最新引流推广方法
  • 做网站是什么软件/淘宝关键词排名优化技巧
  • 泰州网站制作推广/企业网
  • 我自己做网站/焊工培训班
  • wordpress qq在线聊天/网站设计优化
  • 用tomcat做网站/plc培训机构哪家最好
  • 专做校园购物网站/农产品网络营销
  • 网上做网站怎么赚钱/广州百度竞价托管
  • 合肥装饰公司做的好的网站/利于seo的建站系统有哪些
  • 工商管理局注册查询/谷歌seo详细教学
  • 网站设计团队/今天实时热搜榜排名
  • CSS :is () 与 :where ()：简化复杂选择器的 “语法糖”
  • ICCV 2025 | 视频生成迈入“多段一致”新时代！TokensGen用“压缩Token”玩转长视频生成
  • 一文搞定JavaServerPages基础，从0开始写一个登录与人数统计页面
  • 网络 —— 笔记本(主机)、主机虚拟机(Windows、Ubuntu)、手机(笔记本热点)，三者进行相互ping通
  • ENSP防火墙安全策略简单案例
  • k8s简介