Stack Overflow
Stack Overflow

Questions tagged [sift]

Scale-invariant feature transform (SIFT) is an algorithm in computer vision to detect and describe local features in images. This tag is for programming questions related to SIFT implementation or programs that use SIFT algorithm for computer vision applications.

Scale-invariant feature transform (SIFT) is an algorithm in computer vision to detect and describe local features in images, introduced by prof. David Lowe in 2004.

The local features extracted from an image with SIFT can then be used to identify an object from that image. This visualization illustrates homologous SIFT keypoints in two separate pictures of the same magazine cover:

enter image description here

Applications of SIFT include object recognition, robotic mapping and navigation, image stitching, 3D modeling, gesture recognition, video tracking, and match moving.

Algorithm Steps

  • Scale-space extrema detection

  • Keypoint localization

  • Interpolation of nearby data for accurate position

  • Discarding low-contrast keypoints

  • Eliminating edge responses

  • Orientation assignment

  • Keypoint descriptor

More information can be obtained here

837 questions
91
votes
2 answers

What are keypoints in image processing?

When using OpenCV for example, algorithms like SIFT or SURF are often used to detect keypoints. My question is what actually are these keypoints? I understand that they are some kind of "points of interest" in an image. I also know that they are…
dephinera
  • 3,703
  • 11
  • 41
  • 75
71
votes
22 answers

Can't use SURF, SIFT in OpenCV

I'm trying a simple thing like detector = cv2.SIFT() and get this bad error detector = cv2.SIFT() AttributeError: 'module' object has no attribute 'SIFT' I do not understand that because cv2 is installed. cv2.__version__ is $Rev: 4557 $ My system…
Linda
  • 2,375
  • 4
  • 30
  • 33
57
votes
5 answers

How to use SIFT algorithm to compute how similar two images are?

I have used the SIFT implementation of Andrea Vedaldi, to calculate the sift descriptors of two similar images (the second image is actually a zoomed in picture of the same object from a different angle). Now I am not able to figure out how to…
Lazer
  • 90,700
  • 113
  • 281
  • 364
34
votes
3 answers

How does the Lowe's ratio test work?

Suppose I have a set of N images and I have already computed the SIFT descriptors of each image. I know would like to compute the matches between the different features. I have heard that a common approach is the Lowe's ratio test but I cannot…
elena
  • 889
  • 2
  • 11
  • 19
33
votes
6 answers

Sift implementation with OpenCV 2.2

Does someone know the link of example of SIFT implementation with OpenCV 2.2. regards,
Shahgee
  • 3,303
  • 8
  • 49
  • 81
33
votes
6 answers

SURF vs SIFT, is SURF really faster?

I am testing some object detection with SURF and SIFT. SURF claims to be faster and more robust than SIFT but I found in my test that this is not true. SIFT with medium images (600*400) is the same speed of SURF and it recognizes objects pretty well…
dynamic
  • 46,985
  • 55
  • 154
  • 231
29
votes
1 answer

Opencv 3.0 - module object has no attribute 'xfeatures2d'

I have shifted from OpenCV 2.4.9 to 3.0 to make use of drawMatches and drawMatchesKnn function. I came to know that it does not come along with non-free algorithms like SIFT , SURF. So I installed opencv_contrib from…
Pawan
  • 4,249
  • 6
  • 27
  • 32
24
votes
5 answers

Dense sift vs sift?

What is the difference between the dense sift implementation compare to sift? What are the advantages/disadvantages of one to another? I'm talking in particular about the VLFeat implementations.
mugetsu
  • 4,228
  • 9
  • 50
  • 79
21
votes
1 answer

Generate similarity score in percentage from SIFT using opencv

I have been trying to find a way to generate similarity score ( in %) after comparing two images using SIFT in python (2.7.x) opencv (2.4.9). I was only able to find examples that draw lines between matches. How do I proceed with this.
user93
  • 1,866
  • 5
  • 26
  • 45
19
votes
7 answers

SURF and SIFT Alternative Object Tracking Algorithm for Augmented Reality

After asking here and trying both SURF and SIFT, neither of them seams to be efficient enough to generate interest points fast enough to track a stream from the camera. SURF, for example, takes around 3 seconds to generate interest points for an…
Leo Jweda
  • 2,481
  • 3
  • 23
  • 34
19
votes
4 answers

opencv FLANN with ORB descriptors?

I am trying to use FLANN with ORB descriptors, but opencv crashes with this simple code: vector > dbKeypoints; vector dbDescriptors; vector objects; /* load Descriptors from images (with…
dynamic
  • 46,985
  • 55
  • 154
  • 231
18
votes
4 answers

OpenCV Python and SIFT features

I know there is a lot of questions about Python and OpenCV but I didn't find help on this special topic. I want to extract SIFT keypoints from an image in python OpenCV. I have recently installed OpenCV 2.3 and can access to SURF and MSER but not…
Mathieu Dubois
  • 1,054
  • 3
  • 14
  • 22
18
votes
4 answers

Comparing SIFT features stored in a mysql database

I'm currently extending an image library used to categorize images and i want to find duplicate images, transformed images, and images that contain or are contained in other images. I have tested the SIFT implementation from OpenCV and it works very…
Darcara
  • 1,598
  • 1
  • 13
  • 33
16
votes
2 answers

The pro and con of BRIEF and ORB compared to SIFT

I am doing some research in Local Feature representation, so SIFT, SURF and such. Now, has anybody here ever tried BRIEF and ORB? If so, can you discuss what are some of the pro and con with respective to SIFT?
Karl
  • 5,613
  • 13
  • 73
  • 107
15
votes
2 answers

Is sift algorithm invariant in color?

I will use sift in identifying a certain type of object what if that object change in color can it recognize it? i will use opencv library for sift cv2.xfeatures2d.SIFT_create()
jude
  • 360
  • 3
  • 12
1
2 3
…
55 56