SIFT图像特征提取 python3.6 + opencv3.3代码

opencv3.x 中部分函数有改变：

1. SIFT：可以采用help(cv2.xfeatures2d)查询

2.drawKeypoints：同样采用help()方法查询

opencv3 版本sift,surf 及其他不稳定的算法函数都放在opencv3.x的contrib版里。该模块下载地址 https://www.lfd.uci.edu/~gohlke/pythonlibs/

#Python 3.6.2 |Anaconda
import cv2  
import numpy as np  
 
#read image  
img = cv2.imread(r‘test.jpg‘,cv2.IMREAD_COLOR)  
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)  
cv2.imshow(‘origin‘,img);  
  
#SIFT  
detector = cv2.xfeatures2d.SIFT_create()
keypoints = detector.detect(gray,None)  
cv2.drawKeypoints(gray,keypoints,img)  
#img = cv2.drawKeypoints(gray,keypoints,flags = cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)  
cv2.imshow(‘test‘,img);  
cv2.waitKey(0)  
cv2.destroyAllWindows()

技术分享图片

文章来自：https://www.cnblogs.com/P3nguin/p/8135816.html