opencv-python 提取sift特徵並匹配的例項
阿新 • • 發佈:2020-01-09
我就廢話不多說,直接上程式碼吧!
# -*- coding: utf-8 -*- import cv2 import numpy as np from find_obj import filter_matches,explore_match from matplotlib import pyplot as plt def getSift(): ''' 得到並檢視sift特徵 ''' img_path1 = '../../data/home.jpg' #讀取影象 img = cv2.imread(img_path1) #轉換為灰度圖 gray= cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) #建立sift的類 sift = cv2.SIFT() #在影象中找到關鍵點 也可以一步計算#kp,des = sift.detectAndCompute kp = sift.detect(gray,None) print type(kp),type(kp[0]) #Keypoint資料型別分析 http://www.cnblogs.com/cj695/p/4041399.html print kp[0].pt #計算每個點的sift des = sift.compute(gray,kp) print type(kp),type(des) #des[0]為關鍵點的list,des[1]為特徵向量的矩陣 print type(des[0]),type(des[1]) print des[0],des[1] #可以看出共有885個sift特徵,每個特徵為128維 print des[1].shape #在灰度圖中畫出這些點 img=cv2.drawKeypoints(gray,kp) #cv2.imwrite('sift_keypoints.jpg',img) plt.imshow(img),plt.show() def matchSift(): ''' 匹配sift特徵 ''' img1 = cv2.imread('../../data/box.png',0) # queryImage img2 = cv2.imread('../../data/box_in_scene.png',0) # trainImage sift = cv2.SIFT() kp1,des1 = sift.detectAndCompute(img1,None) kp2,des2 = sift.detectAndCompute(img2,None) # 蠻力匹配演算法,有兩個引數,距離度量(L2(default),L1),是否交叉匹配(預設false) bf = cv2.BFMatcher() #返回k個最佳匹配 matches = bf.knnMatch(des1,des2,k=2) # cv2.drawMatchesKnn expects list of lists as matches. #opencv2.4.13沒有drawMatchesKnn函式,需要將opencv2.4.13\sources\samples\python2下的common.py和find_obj檔案放入當前目錄,並匯入 p1,p2,kp_pairs = filter_matches(kp1,kp2,matches) explore_match('find_obj',img1,img2,kp_pairs) # cv2 shows image cv2.waitKey() cv2.destroyAllWindows() def matchSift3(): ''' 匹配sift特徵 ''' img1 = cv2.imread('../../data/box.png',k=2) # cv2.drawMatchesKnn expects list of lists as matches. #opencv3.0有drawMatchesKnn函式 # Apply ratio test # 比值測試,首先獲取與A 距離最近的點B(最近)和C(次近),只有當B/C # 小於閾值時(0.75)才被認為是匹配,因為假設匹配是一一對應的,真正的匹配的理想距離為0 good = [] for m,n in matches: if m.distance < 0.75 * n.distance: good.append([m]) img3 = cv2.drawMatchesKnn(img1,kp1,good[:10],None,flags=2) cv2.drawm plt.imshow(img3),plt.show() matchSift()
以上這篇opencv-python 提取sift特徵並匹配的例項就是小編分享給大家的全部內容了,希望能給大家一個參考,也希望大家多多支援我們。