If you’ve had a chance to play around with OpenCV 3 (and do a lot of work with keypoint detectors and feature descriptors) you may have noticed that the SIFT and SURF implementations are no longer included in the OpenCV 3 library by default.
Unfortunately, you probably learned this lesson the hard way by opening up a terminal, importing OpenCV, and then trying to instantiate your favorite keypoint detector, perhaps using code like the following:
$ python
>>> import cv2
>>> detector = cv2.FeatureDetector_create("SIFT")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: 'module' object has no attribute 'FeatureDetector_create'
Oh no! There is no longer a cv2.FeatureDetector_create method!
The same is true for our cv2.DescriptorExtractor_create function as well:
>>> extractor = cv2.DescriptorExtractor_create("SIFT")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: 'module' object has no attribute 'DescriptorExtractor_create'
Furthermore, cv2.SIFT_create and cv2.SURF_create will fail as well:
>>> cv2.SIFT_create() Traceback (most recent call last): File "<stdin>", line 1, in <module> AttributeError: 'module' object has no attribute 'SIFT_create' >>> cv2.SURF_create() Traceback (most recent call last): File "<stdin>", line 1, in <module> AttributeError: 'module' object has no attribute 'SURF_create'
I’ll be honest — this had me scratching my head at first. How am I supposed to access SIFT, SURF, and my other favorite keypoint detectors and local invariant descriptors if cv2.FeatureDetector_create and cv2.DescriptorExtractor_create have been removed?
The cv2.FeatureDetector_create and cv2.DescriptorExtractor_create were (and still are) methods I used all the time. And personally, I really liked the OpenCV 2.4.X implementation. All you needed to do was pass in a string and the factory method would build the instantiation for you. You could then tune the parameters using the getter and setter methods of the keypoint detector or feature descriptor.
Furthermore, these methods have been part of OpenCV 2.4.X for many years. Why in the world were they removed from the default install? And where were they moved to?
In the remainder of this blog post, I’ll detail why certain keypoint detectors and local invariant descriptors were removed from OpenCV 3.0 by default. And I’ll also show you where you can find SIFT, SURF, and other detectors and descriptors in the new version of OpenCV.
Why were SIFT and SURF removed from the default install of OpenCV 3.0?
SIFT and SURF are examples of algorithms that OpenCV calls “non-free” modules. These algorithms are patented by their respective creators, and while they are free to use in academic and research settings, you should technically be obtaining a license/permission from the creators if you are using them in a commercial (i.e. for-profit) application.
With OpenCV 3 came a big push to move many of these “non-free” modules out of the default OpenCV install and into the opencv_contrib package. The opencv_contrib packages contains implementations of algorithms that are either patented or in experimental development.
The algorithms and associated implementations in opencv_contrib are not installed by default and you need to explicitly enable them when compiling and installing OpenCV to obtain access to them.
Personally, I’m not too crazy about this move.
Yes, I understand including patented algorithms inside an open source library may raise a few eyebrows. But algorithms such as SIFT and SURF are pervasive across much of computer vision. And more importantly, the OpenCV implementations of SIFT and SURF are used by academics and researchers daily to evaluate new image classification, Content-Based Image Retrieval, etc. algorithms. By not including these algorithms by default, more harm than good is done (at least in my opinion).
How do I get access to SIFT and SURF in OpenCV 3?
To get access to the original SIFT and SURF implementations found in OpenCV 2.4.X, you’ll need to pull down both the opencv and opencv_contrib repositories from GitHub and then compile and install OpenCV 3 from source.
Luckily, compiling OpenCV from source is easier than it used to be. I have gathered install instructions for Python and OpenCV for many popular operating systems over on the OpenCV 3 Tutorials, Resources, and Guides page — just scroll down the Install OpenCV 3 and Python section and find the appropriate Python version (either Python 2.7+ or Python 3+) for your operating system.
How do I use SIFT and SURF with OpenCV 3?
So now that you have installed OpenCV 3 with the opencv_contrib package, you should have access to the original SIFT and SURF implementations from OpenCV 2.4.X, only this time they’ll be in the xfeatures2d sub-module through the cv2.SIFT_create and cv2.SURF_create functions.
To confirm this, open up a shell, import OpenCV, and execute the following commands (assuming you have an image named test_image.jpg in your current directory, of course):
$ python
>>> import cv2
>>> image = cv2.imread("test_image.jpg")
>>> gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
>>> sift = cv2.xfeatures2d.SIFT_create()
>>> (kps, descs) = sift.detectAndCompute(gray, None)
>>> print("# kps: {}, descriptors: {}".format(len(kps), descs.shape))
# kps: 274, descriptors: (274, 128)
>>> surf = cv2.xfeatures2d.SURF_create()
>>> (kps, descs) = surf.detectAndCompute(gray, None)
>>> print("# kps: {}, descriptors: {}".format(len(kps), descs.shape))
# kps: 393, descriptors: (393, 64)
If all goes well, you should be able to instantiate the SIFT and SURF keypoint detectors and local invariant descriptors without error.
It’s also important to note that by using opencv_contrib you will not be interfering with any of the other keypoint detectors and local invariant descriptors included in OpenCV 3. You’ll still be able to access KAZE, AKAZE, BRISK, etc. without an issue:
>>> kaze = cv2.KAZE_create()
>>> (kps, descs) = kaze.detectAndCompute(gray, None)
>>> print("# kps: {}, descriptors: {}".format(len(kps), descs.shape))
# kps: 359, descriptors: (359, 64)
>>> akaze = cv2.AKAZE_create()
>>> (kps, descs) = akaze.detectAndCompute(gray, None)
>>> print("# kps: {}, descriptors: {}".format(len(kps), descs.shape))
# kps: 192, descriptors: (192, 61)
>>> brisk = cv2.BRISK_create()
>>> (kps, descs) = brisk.detectAndCompute(gray, None)
>>> print("# kps: {}, descriptors: {}".format(len(kps), descs.shape))
# kps: 361, descriptors: (361, 64)
What's next? We recommend PyImageSearch University.
86 total classes • 115+ hours of on-demand code walkthrough videos • Last updated: October 2024
★★★★★ 4.84 (128 Ratings) • 16,000+ Students Enrolled
I strongly believe that if you had the right teacher you could master computer vision and deep learning.
Do you think learning computer vision and deep learning has to be time-consuming, overwhelming, and complicated? Or has to involve complex mathematics and equations? Or requires a degree in computer science?
That’s not the case.
All you need to master computer vision and deep learning is for someone to explain things to you in simple, intuitive terms. And that’s exactly what I do. My mission is to change education and how complex Artificial Intelligence topics are taught.
If you're serious about learning computer vision, your next stop should be PyImageSearch University, the most comprehensive computer vision, deep learning, and OpenCV course online today. Here you’ll learn how to successfully and confidently apply computer vision to your work, research, and projects. Join me in computer vision mastery.
Inside PyImageSearch University you'll find:
- ✓ 86 courses on essential computer vision, deep learning, and OpenCV topics
- ✓ 86 Certificates of Completion
- ✓ 115+ hours of on-demand video
- ✓ Brand new courses released regularly, ensuring you can keep up with state-of-the-art techniques
- ✓ Pre-configured Jupyter Notebooks in Google Colab
- ✓ Run all code examples in your web browser — works on Windows, macOS, and Linux (no dev environment configuration required!)
- ✓ Access to centralized code repos for all 540+ tutorials on PyImageSearch
- ✓ Easy one-click downloads for code, datasets, pre-trained models, etc.
- ✓ Access on mobile, laptop, desktop, etc.
Summary
In this blog post we learned that OpenCV has removed the cv2.FeatureDetector_create and cv2.DescriptorExtractor_create functions from the library. Furthermore, the SIFT and SURF implementations have also been removed from the default OpenCV 3 install.
The reason for SIFT and SURF removal is due to what OpenCV calls “non-free” algorithms. Both SIFT and SURF are patented algorithms, meaning that you should technically be getting permission to use them in commercial algorithms (they are free to use for academic and research purposes though).
Because of this, OpenCV has made the decision to move patented algorithms (along with experimental implementations) to the opencv_contrib package. This means that to obtain access to SIFT and SURF, you’ll need to compile and install OpenCV 3 from source with opencv_contrib support enabled. Luckily, this isn’t too challenging with the help of my OpenCV 3 install guides.
Once you have installed OpenCV 3 with opencv_contrib support you’ll be able to find your favorite SIFT and SURF implementations in the xfeatures2d package through the cv2.xfeatures2d.SIFT_create() and cv2.xfeatures2d.SURF_create() functions.
Join the PyImageSearch Newsletter and Grab My FREE 17-page Resource Guide PDF
Enter your email address below to join the PyImageSearch Newsletter and download my FREE 17-page Resource Guide PDF on Computer Vision, OpenCV, and Deep Learning.
Hi Adrian,
First of all: Thank you very much for your effort!:) you said that you will cover the building process of opencv3 using the raspberry pi. Could you please consider including tbb when compiling opencv? Without tbb it’s not possible to leverage from all four cores. Unfortunately I was not able to compile it with tbb support, this seems to be due to a problem with raspbian wheezy.
Thank you very much in advance:)
Hey Max, thanks for the comment. I already have the tutorial drafted, but I’ll go back and see if I can include tbb — at the very least it could make for a good followup post.
Hey Adrian,
is using ORB, which isn’t patented and is written by the OpenCV guys, instead of SIFT or SURF no reasonable alternative? I have only a bit experience with it but so far it had given good results. I’d still have to compare them directly though to be able to tell if there’s a difference.
There are many, many alternatives to SIFT and SURF. ORB is one. BRIEF, BRISK, FREAK, KAZE, and AKAZE are others. Choosing between them is very much application specific and I recommend trying the options, examining the accuracy, and then making the educated choice from there. I hope that helps!
Will this method work windows too? and if firstly unzip open cv from source directly and then perform this tutorial will this work. can u provide basics steps for installing it on windows too.
I don’t own a Windows system and haven’t used the OS in 8+ years at this point. The tutorials covered in this blog mainly focus on OSX, Ubuntu, and Raspbian (for the Raspberry Pi). For help with Windows and OpenCV, I would consult the official OpenCV documentation.
Hi Adrian, ria.
Firstly, thanks a lot Adrian for your excellent and comprehensive tutorials and blogs – they’re most helpful, and truly appreciated.
Just thought to mention that in windows a simple- “pip install opencv-contrib-python” installed the required packages for SIFT and SURF.
Thanks again for everything,
Binymain
Hey Binymain, thanks for the comment. I’m doing some testing with the pip-installable versions of OpenCV and Python. One aspect to be aware of is that you may lose GTK support which enables functions like
cv2.imshow. I’ve seen this happen in a few occasions. I’m currently testing it myself, but want others to be aware of this.Hi Adrian and Binymain,
I just tried to add SIFT and SURF on my windows 10 machine using “pip install opencv-contrib-python” but it still gives me the error that the attribute SIFT does not exist. Though the pip command itself completed succesfully. I ran the pip in my Python27 folder.
Sorry, I can not confirm yet whether GTK support is still there or not.
Thanks,
Wim
Thank you for sharing, Wim!
hi adrian, i like your posts so much, i am running a code in windows pycharmin which i have used this line
surf=cv2.SURF(hessian)
and it gives following error
surf=cv2.SURF(hessian)
AttributeError: module ‘cv2.cv2’ has no attribute ‘SURF’
Process finished with exit code 1,
in your post you said we should install opencv and opencv_contribution, so as i did but can’t understand further? what should i do now?
I assume you installed OpenCV via pip? If so, you need to instead compile from source. I have a number of OpenCV install guides that you can follow but the gist is that SIFT and SURF are not available in the pip installs of OpenCV.
I just installed a fresh version of Jessie on my Raspberry Pi 2.
Apparently OpenCV 2.4.9.1 is included in that build.
However, like OpenCV 3.0, it appears that xfeatures2d is not there either.
I get the following error:
AttributeError: ‘module’ object has not attribute ‘xfeatures2d’
I’ll try to do the install as described above to see if it resolves the problem.
OpenCV 2.4.9 is included in Jessie? Interesting. I did not know that.
However, if you’re looking to use SIFT, SURF, etc. in OpenCV 2.4.X, you’ll need to use the
cv2.FeatureDetector_createandcv2.DescriptorExtractor_createmethods.>>> import cv2 >>> image=cv2.imread("bean.jpg") >>> gray=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY) >>> sift=cv2.xfeatures2d.SIFT_create() Traceback (most recent call last): File "", line 1, in AttributeError: 'module' object has no attribute 'xfeatures2d'Again I got this error. Sir, can you please provide me any solution.?
Please follow my OpenCV 3 install instructions for your particular OS and Python version here. Be sure to pay attention to the section on installing the
opencv_contribmodule — this is where optional modules such asxfeatures2dwill be compiled and installed.import cv2
cv2.__version__
Which version?
This is a life saver! Thanks for this post!!!!
No problem Gerard, I’m happy it helped!
Hi, I’m really new in OpenCV and I need to use Sift and Surf in Matlab. I did every thing you say here and now I have the .cpp functions but I don’t know how to import them to Matlab. Do you know how to? I will appreciate for this.
Sorry, I only use OpenCV + Python this blog. It’s been a good many years since I’ve had to use MATLAB. I would suggest using the Image Processing Toolkit for MATLAB or better yet, using David Lowe’s implementation of SIFT in MATLAB.
thanx very helpful..plz im clustering images.. how can i pass those features as vector to kmeans
You would first need to construct a bag of visual words model, which involves:
1. Extracting feature vectors from all your images.
2. Clustering these features to build a codebook.
3. Quantizing the features associated with each image into the codebook to form your histogram of visual words.
4. Finally, you can take this resulting histogram and pass it on to k-means.
I detail how to build the bag of visual words model from the ground up inside PyImageSearch Gurus. Be sure to take a look!
thnxxxxxx..plz, before extracting features, image doesnt need any pre processing??
That depends entirely on your dataset. Normally conversion to grayscale, resizing, and perhaps a bit of Gaussian smoothing. But that is again entirely dependent on your dataset.
Hey adrian,
SIFT in opencv3 is up and running smooth, thanks for the tutorial. But there are other issues too in opencv3(like cv2.cv.Scalar(10,20,0)) this is not present in new version. Is there any way i can set opencv 2.4 for my old projects in pycharm and opencv3 for new projects. thanks!!
Correct, anytime you see
cv2.cvthis should be a red flag that the code will not run in OpenCV 3 — this is because the oldcv2.cvsub-module is not included. However, a Scalar in OpenCV 3 (and OpenCV 2.4) should just be represented as a tuple. I would suggest creating a separate virtual environment for your OpenCV 3 install, and then configure it with PyCharm.You are rockstar….. thanks for this post.
Hi Adrian. Actually i was stuck in how to compile opencv again with opencv contrib . I am using PyCharm for building programs and my OS is Windows.What to do to compile the file opencv3 with opencv-contrib??
Hey Simran — I don’t support Windows on the PyImageSearch blog. I do provide support for Ubuntu, OSX, and Raspbian, and in all honesty, if you want to learn computer vision you should be using a Unix-based OS (unless there is some very specific Microsoft functionality that you need). I provide install instructions on this page. And I also offer a pre-configured Ubuntu virtual machine as part of Practical Python and OpenCV.
Hey! Thanks man! this post was really helpful. one more thing… what will be the substitute for cv2.DescriptorExtractor_create(“SIFT”) ?
As detailed in the blog post, the substitute is:
sift = cv2.xfeatures2d.SIFT_create()You can detect keypoints via:
kps = sift.detect(image)And then extract features via:
(kps, descs) = sift.compute(image, kps)hello, do you mean that the substitute for cv2.FeatureDetector_create(“SIFT”) and cv2.DescriptorExtractor_create(“SIFT”) are the same?
I would like to access attributes like sift.upright as well. How can I do that?
I wasn’t aware
sift.uprightwas an attribute. Can you link to the documentation you are seeing forsift.upright?Hi Adrian, I also tried to work with SIFT but gave me and error in the VirtualMachine, I wanted to ask if opencv_contrib is also installed in VirtualMachine? and if not is there any clean way to add it to the existing VirtualMachine without starting to install OpenCV from scratch?
Hi Mojtaba — are you referring to the VM included in Practical Python and OpenCV? If so, yes, the opencv_contrib packages are included in the OpenCV installation. If you are getting an error message, please share it so we can resolve the issue.
Thanks Adrian, Yes I mean the VirtualMachine in Practical Python and OpenCV course. I get this error for this line of code :
my code : sift = cv2.SIFT()
module object has no attribute ‘SIFT’
I’ll appreciate if you can help me with this.
Thanks again very much for your help
Hi Mojtaba — please read the contents of this blog post. In OpenCV 3, you can access SIFT via:
sift = cv2.xfeatures2d.SIFT_create()This has saved my time.
Fantastic, I’m glad to hear it Joel 🙂
Hi Adrian, How do I create Dense features as such in Opencv 2.4.x –
FeatureDetector_create(“Dense”). Is there an equivalent in Opencv 3.2 ?
Please let me know how do I do this ?
In OpenCV 2.4, you can create the Dense feature detector via:
detector = cv2.FeatureDetector_create("Dense")However, as far as I know, there is no Dense keypoint detector in OpenCV 3. You need to loop over the pixels and create a KeyPoint object for each.
I really appreciate the effort you have put into these tutorials. Thank you so much.
Thanks Vitalis!
Is there anyone could suggest how or which part to change in the SIFT Opencv to read 3D data instead of 2D images?
Thank you so much! I had just installed opencv-contrib-python on pip, on Ubuntu 16.04.
Wish you all the best.
Thanks for the brilliant post and also for the tips on installing opencv 3.1 on Ubuntu. you rock!
Thanks Prabhakar! I’m happy you found the tutorial helpful 🙂
Hello Adrian,
First off, thank you for sharing your knowledge. I have been following your blog for some time now.
I have installed opencv3. I have opencv 3.2 with python 2.7.
When I get opencv information via brew info opencv I can see that it has been installed with contrib.
Even then, I am not able to use xfeatures2d. SIFT and SURF still throw attribute errors.
Can you please help.
Thanks.
How are you instantiating your SIFT and SURF objects?
I have instantiated it as mentioned in your blog.
How did you install OpenCV 3? It sounds like the opencv_contrib modules were not compiled and installed correctly.
WHOA You literally save my day!!! I’m about to reinstall opencv. Thumbs UP!
Wonderful, I’m glad to hear it Allan!
Hi Adrian
First of all I want to thanks to you for your helps,
I can install opencv3 and opencv contrib module thanks to your blog but I am studying SURF algorithm my university project in c++ On the other hand surf which inside opencv contrib module works for python unfortunetly I am should use c++ How can surf work c++ in opencv 3 contrib
Hi Gozde — thanks for the comment, but I haven’t used the SURF C++ bindings so I’m not particular sure. Sorry I couldn’t be of more help here and best of luck with your project.
Hi , thank you for this post, however, when i try to visualize the result using imshow i get error i even tried to plt from matpolib the error ‘Image data cannot be converted to float’
Please is there anything i can do.
Hey Suraj — is there a reason why you are trying to display the image via matplotlib? I would also double-check that the image you are trying to display is a NumPy array. It sounds like you may have a non-OpenCV formatted NumPy array, perhaps as the result of a bug/logic flow issue earlier in the script.
Hi, I installed Opencv3.4 on Raspbian stretch to my raspberryPi 3 using your tutorial (I didn’t set OpenCV Virtual environment).The installation completed and opencv could be imported without error. but when I use “sift = cv2.xfeatures2d.SIFT_create()”. An error appears that xfeatures2d is not available that because of not setting up virtual environment . if else please help me with this
It sounds like you did not install OpenCV with the “contrib” module. Go back to your “cmake” step and ensure “xfeatures2d” is listed in the list of modules to be built. My guess is that your path to the contrib modules directory is incorrect.
Hi Adrain, I have the same error, I followed your download steps and downloaded OpenCV 3.4.1. I am certain that I downloaded the same version of the contrib files and they unzipped correctly. Yet whenever I try a program that includes that includes anything like the code above or something like the code given in line 22 of the center of contour blog post I keep getting the same error:
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
AttributeError: module ‘imutils’ has no attribute ‘is_cv2’
Any suggestions as I am unable to figure it out??
Your error here doesn’t have anything to do with OpenCV, it’s related to the “imutils” library. Make sure you have installed an updated version of imutils:
If you have a directory named ‘imutils’ in your working directory you should delete it as it will confusing the Python interpreter on which module to use.
Can you include a build opencv-python tutorial on windows ?
Sorry, I don’t support Windows here on PyImageSearch. I highly recommend you use Linux (such as Ubuntu) or macOS for studying computer vision.
hello adrian.
thank you for interesting post.
I install opencv3.4 on my system. but when I’m using SIFT, say’s me that you can’t use this module . because this is non free module. when I removed OpenCV3.4 and install OpenCV 3.2 this problem is not shown.
Can you help me why this happen is accrued ?
It sounds like you installed OpenCV without the NON_FREE module enabled. Follow my OpenCV install guides to obtain the full install.