Geek Answers Handbook

OpenCV cannot find ORB

In a previous question, I found out that I had to install opencv-contrib in order to use OpenCV Python with external modules such as SIFT. However, in my project I want to use ORB or something similar. cv2.ORB() does not work, but cv2.xfeatures2d.ORB_create() or any other command agglutination.

As SO knows, OpenCV has pretty poor documentation for its Python API.

How to use ORB to map functions in OpenCV Python?

MWE :

 #!/usr/bin/python2.7 import numpy as np import cv2 from matplotlib import pyplot as plt img = cv2.imread('smallburger.jpg',0) # Initiate STAR detector orb = cv2.ORB() # find the keypoints with ORB kp = orb.detect(img,None) # compute the descriptors with ORB kp, des = orb.compute(img, kp) # draw only keypoints location,not size and orientation img2 = cv2.drawKeypoints(img,kp,color=(0,255,0), flags=0) plt.imshow(img2),plt.show()

CLI Output:

 Traceback (most recent call last): File "./mwe.py", line 9, in <module> orb = cv2.ORB() AttributeError: 'module' object has no attribute 'ORB'
+5
source share
2 answers

Stupid OpenCV. It is just cv2.ORB_create() .

+9
source

Here you have my training code

  def featureMatchingBF(self,img1,img2,method): corners = cv2.goodFeaturesToTrack(img1, 7, 0.05, 25) corners = np.float32(corners) for item in corners: x, y = item[0] cv2.circle(img1, (x,y), 5, (255,0,0)) cv2.imshow("Top 'k' features", img1) cv2.waitKey() #======================================================================= # (H1, hogImage1) = feature.hog(img1, orientations=9, pixels_per_cell=(6, 6), # cells_per_block=(2, 2), transform_sqrt=True, visualise=True) # hogImage1 = exposure.rescale_intensity(hogImage1, out_range=(0, 255)) # hogImage1 = hogImage1.astype("uint8") # cv2.imshow("Input:",img1) # cv2.imshow("HOG Image", hogImage1) # cv2.waitKey(0) #======================================================================= if method is "ORB": #Compute keypoints for both images kp1,des1 = self.computeORB(img1) kp2,des2 = self.computeORB(img2) #=================================================================== # for i,j in zip(kp1,kp2): # print("KP1:",i.pt) # print("KP2:",j.pt) #=================================================================== #use brute force matcher for matching descriptor1 and descriptor2 bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True) # Match descriptors. matches = bf.match(des1,des2) # Sort them in the order of their distance. matches = sorted(matches, key = lambda x:x.distance) self.filterMatches(matches) # Draw first 10 matches. img3 = cv2.drawMatches(img1,kp1,img2,kp2,matches[:20], flags=2,outImg = img1) #show result cv2.imshow("Matches",img3) cv2.waitKey(0) def computeORB(self,img): #Initiate ORB detector orb = cv2.ORB_create() #find keypoints kp = orb.detect(img,None) #compute despriptor kp, des = orb.compute(img,kp) # draw only keypoints location,not size and orientation img2 = cv2.drawKeypoints(img, kp, None, color=(0,255,0), flags=0) #plt.imshow(img2), plt.show() return kp,des
+1
source

More articles:


All Articles