python-應用OpenCV和Python進行SIFT算法的實現

如下圖為進行測試的q和h，分別驗證基於BFmatcher、FlannBasedMatcher等的SIFT算法

代碼如下：

import numpy as np
import cv2
from matplotlib import pyplot as plt


imgname1 = 'G:/q.jpg'
imgname2 = 'G:/h.jpg'

sift=cv2.xfeatures2d.SIFT_create()
img1 = cv2.imread(imgname1)
gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY) #灰度處理圖像
kp1, des1 = sift.detectAndCompute(img1,None)   #des是描述子

img2 = cv2.imread(imgname2)

gray2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)#灰度處理圖像
kp2, des2 = sift.detectAndCompute(img2,None)  #des是描述子

#hmerge = np.hstack((gray1, gray2)) #水平拼接
#cv2.imshow("gray", hmerge) #拼接顯示為gray
#cv2.waitKey(0)

#img3 = cv2.drawKeypoints(img1,kp1,img1,color=(255,0,255)) #畫出特征點，並顯示為紅色圓圈
#img4 = cv2.drawKeypoints(img2,kp2,img2,color=(255,0,255)) #畫出特征點，並顯示為紅色圓圈

#hmerge = np.hstack((img3, img4)) #水平拼接
#cv2.imshow("point", hmerge) #拼接顯示為gray
#cv2.waitKey(0)

# BFMatcher解決匹配
bf = cv2.BFMatcher()
matches = bf.knnMatch(des1,des2, k=2)
# 調整ratio
good = []
for m,n in matches:
    if m.distance < 0.75*n.distance:
        good.append([m])

img5 = cv2.drawMatchesKnn(img1,kp1,img2,kp2,good,None,flags=2)

cv2.imshow("BFmatch", img5)
cv2.waitKey(0)
cv2.destroyAllWindows()

效果如下：