We’re rewarding the question askers & reputations are being recalculated! Read more.

Questions tagged [sift]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
66
votes
4answers
49k views

What are some free alternatives to SIFT/ SURF that can be used in commercial applications?

As far as I understand, both SURF and SIFT are patent protected. Are there any alternative methods that can be used in a commercial application freely? For more info on the patent check out: http://...
16
votes
5answers
16k views

Scale and Rotation invariant feature descriptors

Can you list some scale and rotational invariant feature descriptors for use in feature detection. The application is for the detection of cars and humans in video captured by a UAV, using a multi-...
15
votes
2answers
6k views

Why is the difference of gaussians scale space scale invariant?

I'll use the Scale-invariant feature transform algorithm as an example here. SIFT creates a scale space based on scaled gaussian filtering of an image, and then computes the difference of gaussians ...
13
votes
3answers
4k views

Is sift a good way to extract features from an image?

I am trying to extract features from an image, but I have failed to get the points that I want to extract, and hence my image fails to match with the template. Are there any checkpoints that I have ...
12
votes
1answer
16k views

Image classification using SIFT features and SVM

I am hoping someone can explain how to use the bag of words model to perform image classification using SIFT/SURF/ORB features and a support vector machine? At the moment I can compute the SIFT ...
10
votes
3answers
2k views

Detecting a filled glass object

I've been sent here from this question in stackoverflow, please excuse me if the question comes too specific and it's not in the manners in here:) The task is to find a glass with specific liquid in ...
9
votes
1answer
304 views

What is the story behind the story about SIFT descriptor?

The following is from Lowe 2004 paper ( http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf ). One obvious approach would be to sample the local image intensities around the keypoint at the appropriate ...
4
votes
2answers
1k views

SIFT - why s+3 scales per octave?

I have a problem with SIFT that I do not understand. Lowe [1] proposed in his work the s=3 levels of scale are enough for one octave. Afterwards, he mentioned that ...
4
votes
2answers
4k views

Why optical flow ? why not tracking

I have a question that might be stupide ! Supposing that I try to detect object moving in a video or human action. Many works are based on optical flow computation. My question is why using OF is ...
4
votes
1answer
196 views

What scale should a detected SIFT point be extracted at?

I've heard this from a few different researchers but I can't find a definitive value. Given the "scale" extracted by David Lowe's SIFT detector, we need to extract a descriptor at a specific scale. ...
4
votes
1answer
88 views

What Is “Description Vector” in Image Processing?

When we want to use classifiers like SVM, we first should extract descriptors using algorithms like SIFT. But I have a question which might call a silly one: Let's assume $$ \begin {equation} D_a=\{...
3
votes
2answers
4k views

Why is it necessary to implement octaves in sift

I've been studying sift very hard for two weeks. I found much materials about scale space. It is very hard to understand scale space depthly. What I've found and confusing things are that 'scale' in ...
3
votes
0answers
2k views

Creating a Gaussian Pyramid

I'm trying to recreate a gassuain pyramid using the following scales: There seems to be two concepts used here: 1) When an image is halved, applying a gaussian kernel of σ will apply as 2σ. 2) When ...
2
votes
2answers
114 views

Would the locations of SIFT features generally agree with features detected by Shi-Tomasi method?

I am having a comparison of different feature detection methods. So if we compare the SIFT (Scale-invariant feature transform) and Shi-Tomasi method, will their feature locations agree and why? Are ...
2
votes
3answers
1k views

Intuitive understanding of scale-space extrema detection

Can someone explain intuitively why local maxima and minima in the scale-space domain make for good keypoints? I understand using LoG or DoG zero-crossing points to identify spacial variations, i.e. ...
2
votes
1answer
2k views

Using ROC curves for comparing the performance of SIFT and SURF

I want to compare the performance of SIFT and SURF against some standard image set. After a bit of research, I found that ROC curves are one of the best ways to do this task. In order to plot ROC ...
2
votes
1answer
118 views

Why Does the Odd Multiple of $ \frac{\pi}{4} $ on Gaussian Cause Loss in Repeatability Under Image Rotations?

I couldn't figure out below paragraph on SURF paper and hope that someone can help me to understand it. Why image rotations around odd multiples of $\frac{\pi}{4}$ lead to a loss of repeatability? ...
2
votes
3answers
1k views

Visualize visual words in bag of words model

I am implementing visual bag of words through these steps: Find interest points using SIFT Calculate SIFT descriptor Build codebook through kmeans clustering of SIFT descriptors. How can I visualize ...
2
votes
1answer
4k views

SIFT - Taylor Expansion

I'm trying to implement SIFT algorithm. After I found the min/max points in DOG images I need to find the real min/max subpixels by taylor exapnsion: $$ \begin{equation} D(\mathbf{x}) = D + \frac{\...
2
votes
0answers
175 views

Affine detector + SIFT descriptor

I am approaching to the Oxford Buildings dataset which contains already computed SIFT descriptors from affine detected keypoint locations. Usually SIFT detector provides to its detected keypoints ...
2
votes
2answers
1k views

Object-Recognition using SIFT: Switching the order of images creates two different results

I've developed a large test-system which can use every interest-point-detector and -descriptor. I use it for evaluation of the given algorithms with the standford-image-collection of cd-covers. This ...
1
vote
1answer
364 views

Keypoint position and scale in SIFT

If I understood it right, a keypoint is a tuple $$(x,y,\sigma, r),$$ where $x,y$ define the position of the keypoint and $r$ an orientation (given by the most domiant gradiant vector around the ...
1
vote
1answer
139 views

I have a question on SIFT

I am reading a paper on SIFT by Lowe. In it, gradient magnitudes and orientations are calculated using these formulae: $$$$ I don't know why m(x,y) is calculated above. I heard that gradient ...
1
vote
3answers
992 views

How to proceed for BOW creation From sift features

I extracted sift feature to construct a bag-of-words model. I did the following to extract the feature vector: Extracted features from the key frames. After the feature extraction I tried using ...
1
vote
2answers
829 views

Why is scale space (DoG) needed to detect scale invariant features?

I would have a theoretical question, about the detector part of the SIFT algorithm, which as it is explained by D. Lowe in his paper, used the DoG to detect keypoints in an input image. Problem ...
1
vote
1answer
407 views

How to recognize an object from a small training set of images?

Given a small training set of images (say, around 6 max) of the same object, how to measure how likely is another query image to contain the given object? The training images are "clean", i.e. only ...
1
vote
2answers
860 views

what is the output of BoW after an image has been trained with SIFT algorithm and k-means

SIFT algorithm provides a 128 dimensional feature vector that is used for image classification.When all the interest points(key points) are taken together and K-means clustering is applied,the image ...
1
vote
1answer
917 views

What steps come after finding the gradients of the SIFT key points?

I am using a SIFT algorithm to extract features from an image. I understand that the SIFT descriptor first finds the extrema and then finds the gradient and direction of each of these interest points....
1
vote
0answers
240 views

VLFEat: How to extract the SIFT descriptor without SIFT feature detection?

I am using the MATLAB interface to the VLFeat toolbox in order to calculate a SIFT descriptor for image patches extracted around key points. Due to the greater framework of what I'm doing, I cannot ...
1
vote
0answers
37 views

Analytical expression for salient Blob detection in scale space

I am working on exact mathematical expression which can be obtained in image processing tasks.(I do not know much about image processing but my work is more mathmatical) In Gaussian scale space, we ...
1
vote
1answer
219 views

Can SIFT run in realtime?

What is the best possible runtime for extracting SIFT keypoints and Descriptors? I know it depends on #keypoints extracted. So, say for image of size 640x640, the code that I have been using requires ...
1
vote
0answers
66 views

Geometric models to discard image features

I am working on the implementation of a location recognition pipeline as detailed in the section 5.4 of the paper Leveraging 3D City Models for Rotation Invariant Place-of-Interest Recognition: ...
1
vote
1answer
121 views

Image Projection with SIFT

Recently, I am thinking about a problem regarding image projection. I have a larger picture as bellow. I want to find the transformation matrix, x'=Hx. When the above image pass the transformation ...
0
votes
1answer
81 views

SIFT About Difference-of-Gaussian function extrema?

How to get formula (2) by formula(1)?
0
votes
1answer
163 views

Hessian Matrix. Second partial derivative test

I have a question about the hessian matrix / determinant of the hessian matrix. For the Hessian matrix, one is able to determine the local curvature around a point. And with the Second partial ...
0
votes
1answer
77 views

need general resource about image matching

i'm working on image matching mainly SIFT and SURF for my thesis. i read Moravec's and harris corner detectors and understand them quiet well in my own opinion.A COMBINED CORNER AND EDGE DETECTOR[1] ...
0
votes
2answers
209 views

Increasing Recall rate for SIFT

Is there a better way to increase Recall Rate when using SIFT features? I am thinking a way to replace the NN1/NN2 ratio to account for slightly distorted objects. Moving towards clustering and using ...
0
votes
1answer
425 views

Segmentation step when using feature descriptors

In my final year project, we are using a SIFT feature descriptor to classify and recognize objects, but I have never come across segmentation in the process of image classification/categorization. ...
0
votes
1answer
2k views

taylor expansion of scale space function

I see the following expression from http://en.wikipedia.org/wiki/Scale-invariant_feature_transform The quadratic Taylor expansion of the Difference-of-Gaussian scale-space function, with the ...
0
votes
0answers
29 views

SIFT between 1 image and dataset (2 images)

I use SIFT, and I want to find the angle of inclination of an image compared to two reference images, in short: I have 3 images : Image x: input image Two images 1 and 2, reference images that are ...
0
votes
0answers
13 views

Efficient image matching technique for small match library set

Background A scene captured from video frames from an Android mobile device camera are to be analyzed in real-time. The scene will contain up to 12 distinct photos. The library images to be matched ...
0
votes
1answer
331 views

Laplacian of Gaussian Approximation and Gaussian Blur as the Solution of Heat Equation

While I was reading SIFT paper(Lowe, 2004), I came across the method that he apply "heat diffusion equation" to Gaussian function to derive that $$ \frac{∂G}{∂σ} = σ∇^2G $$ I searched Wikipedia and ...
0
votes
0answers
104 views

How to obtain the relative position (coordinates) of SIFT feature from image center coordinates?

I have extracted SIFT features (keypoints and descriptors) of training set and saved in an inverted index form. My question is how can I calculate the coordinates of each visual features in an image ...
0
votes
0answers
39 views

Counting percentage of fouling on a surface

I am completely new to image processing and python. I hope I can find some help here. I am trying out a project on detecting fouling% on a ship hull using raspberry pi. I am trying to learn how this ...
0
votes
1answer
945 views

k-NN match for object recognition

The $\frac{d_1}{d_2}<0.6$ gives a large number of false matches and it assumes the nearest neighbour is a correct match. Anybody knows any good method to reduce number of false matches or filter ...
0
votes
1answer
431 views

Which is the best method for comparing the histogram obtained after BOW?

Euclidian distance Cosine similarity Histogram Intersection Or any other? Consider the importance of the method in case of images. Eg, Cosine Similarity matches angle of two vectors... What impact ...
0
votes
0answers
546 views

Distance-metric for SIFT descriptors matching

Will using Cosine-Similarity or Histogram Intersection as distance-metric, for matching SIFT descriptors, help to get better results? Anybody tried on that ever?
0
votes
1answer
230 views

Is there two Types of Scale Space in SURF algorithm?

I couldn't figure out below paragraph on SURF paper and hope that someone can help me to understand it. Bay H., Ess A., Tuytelaars T. Van Gool L. - Speed-Up Robust Features (SURF), page 4, ...