File Exchange

image thumbnail

SIFT (Scale invariant Feature Transform) Algorithm

version 1.0 (715 KB) by

This code gives you the SIFT keys and their descriptors for a given image.

79 Downloads

Updated

View License

Two codes have been uploaded here. Out of these 'keypointsdetectionprogram' will give you the SIFT keys and their descriptors and 'imagekeypointsmatchingprogram' enables you to check the robustness of the code by changing some of the properties (such as change in intensity, rotation etc).Then you can check the matching percentage of key points between the input and other property changed image by using the key point locations using this code.You can select the images and properties from the options given in the command window.

Comments and Ratings (27)

Nimit Kaura

hello Sir,
how can a save a file with .SIFT extension

purushotham e

Hi, in the code store2 and store3 variables are used to store 2nd and 3rd level pyramid generation, but those values are never used. why we need to compute those values?

renu gowtham

Hi sir, i need detail explanation for where we improve the key point performance in your code of key point detection and key point matching.

eugen heinz

smart code!

MATHAVARAJA A

please give me a detailed description of how the sift algorithm working in an images

ceyhun

ceyhun (view profile)

Mallika Pant

I need to enquire about the issue i.e how can i create a training matrix of many same dimension images as i am facing issue in concatenating the descriptors as diff no of descriptors are coming for different images

Debabrata

Hi mr. Naveen,
sir, can you please give me comments on the code. I really can't understand this

Hi Naveen,
Thanks for your great work.

I've several problems here. Firstly, Lowe has mentioned that each key-point should be an extrema in comparison with its 26 neighbors which are selected from last, present and next scale. But you have used present and next scales. Moreover, your formula for finding gradient and orientation is somehow different from Lowe's paper. Can you enlighten me here?

Kirti Wanjale

Hello Naveen,
Thanks for great work! I just wanna to know how to find final number of keypoints from your keypointdetectionprogram.m program

Soukaina

Hi,

Great work Naveen.
Thank you.

Hi Naveen,
Is this coding is suitable for signature recognition system? please advice.
Thanks

Hossein

Hossein (view profile)

Hi Mr Nveen
you calculate DOG image(store1, store2,store3) while you just used store1(DOGs in first octave) to determine etremas and as result the key points.
In the original paper it has been mentioned that all key point in all octave shoud be considered.

Hossein

Hossein (view profile)

Shan

Shan (view profile)

Hi Naveen,

Nice work. I have one question. In your 'keypointsdetectionprogram' code, kpmag and kpori are calculated in Forming key point neighbourhooods part, but they are not used in creating the descriptors. However, a similar process is carried out in the descriptor creation part. I'm confused about that.

In the SIFT algorithm, a histogram of 36 bins is created in orientation assignment but a histogram of 8 bins is created for each sub region. What is the use of the former one?

Thanks.

anum eman

Ganesh

Ganesh (view profile)

Hi Naveen,
Thanks for the reply. Actually I`m kinda new to SIFT. I need your advice on the details as described below:

1) You have only used the information form 1st octave only, (store1) to find the keys point. Why didnt you use the information of store 2 and store 3 to find the keypoints?

2) For finding the keypoints, you have only used my,mz, miy and miz. Why didnt include mx and mix for example, i2(i,j)>my && i2(i,j)>mz) && i2(i,j)>mx) || (i2(i,j)<miy && i2(i,j)<miz && i2(i,j)<mix).

Please advice. Thanks for your help.

Achu m k

hi naveen,
its a great work.
Could you please tell me were to find the equations you used in the program?

Ganesh

Ganesh (view profile)

Hi Naveen,
Great work!
Anyway, did you include the accurate key-point localization and eliminating edges codes this program? Please advice.

shaaban

Ricardo

Hi Cheggoju. Well, I sort of understand what you mean about not using keywords, you can still speed up by preallocating memory and by using more matrix multiplication instead of for loops. Even if you still want to keep for loops, the inner loop should always be the one with more iterations.
Anyway some numerical calcs have optimized solutions which exist for many years and at some point, at least professionaly, it will be almost impossible to use only your own code. Such is the case of FFT. Best wishes.

Thank you for your comment @Ricardo.
I prefer using my own coding over keywords so I used my own code. Thank you for your suggestion.

Ricardo

Nice work but could be polished a bit. Most of the for loops used in convolution should be replaced by calls to conv2() or some DFT/FFT/FFTW based algorithm (convolution to product in the frequency domain and back). Preallocating memory (c = zeros(m,n), etc) will also help. The code will become much faster (about 60 times in my laptop). Any relation between your code and the one submitted by vijay anand? They appear to be the same.

MATLAB Release
MATLAB 7.11 (R2010b)
Acknowledgements

Inspired: SIFT Feature Extreaction

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.

» Watch video