CODEWITHSUNDEEP
python-2.7opencvfedora-23
Pedro
Pedro

Reputation: 331

No SIFT detector on OpenCV 2.4.12

I'm trying to use the SIFT detector under Fedora 22, using Python 2.7.10 and OpenCV 2.4.12. As for instalation all I did was sudo dnf install opencv* and let it install all the dependencies, but upon trying to run the sample code bellow, I was greeted with the error: 

Traceback (most recent call last):  
File "features.py", line 47, in <module>  
sift = cv2.SIFT()  
AttributeError: 'module' object has no attribute 'SIFT'

I think this means that Python isn`t being able to find the SIFT library, am I correct? How do I fix this?

Sample Code:

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

MIN_MATCH_COUNT = 10

img1 = cv2.imread('poste_blur.jpg',0)          # queryImage
img2 = cv2.imread('poste.jpg',0) # trainImage

# Initiate SIFT detector
sift = cv2.SIFT()

# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1,None)
kp2, des2 = sift.detectAndCompute(img2,None)

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)

matches = flann.knnMatch(des1,des2,k=2)

# store all the good matches as per Lowe's ratio test.
good = []
for m,n in matches:
    if m.distance < 0.7*n.distance:
        good.append(m)

if len(good)>MIN_MATCH_COUNT:
    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)

    M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC,5.0)
    matchesMask = mask.ravel().tolist()

    h,w = img1.shape
    pts = 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

draw_params = dict(matchColor = (0,255,0), # draw matches in green color
                   singlePointColor = None,
                   matchesMask = matchesMask, # draw only inliers
                   flags = 2)

img3 = cv2.drawMatches(img1,kp1,img2,kp2,good,None,**draw_params)

plt.imshow(img3, 'gray'),plt.show()

Upvotes: 0

Views: 446

Answers (1)

Dragos Stanciu
Dragos Stanciu

Reputation: 320

As berak has suggested, if you need to use SURF or SIFT, you need to compile OpenCV from sources. You should definitely uninstall the current version first.

I think on Fedora you could use something like:

sudo dnf erase opencv*

I would also do a sudo updatedb and a locate opencv to find all remaining OpenCV files. You should then delete these manually.

Upvotes: 0

Related Questions