how to increase no of point of interest in SIFT program

Question

0.00/5 (No votes)

See more:

Hi friend, currently i am working on a project in which i have to use SIFT(Scale invariant future transform). Actually I want to develop an application like search engine in that i want to get know user intension when he click on any image in web browser. when he click on any image i want to show similar types of images from my database on browser.In this process i have to strictly implement SIFT algorithm.
I have SIFT project but when i run that SIFT project & give my images as input and change keyPoint combobox & select as 1300 or "double input size" or gives any large number in all case it does not gives me more than 1028 kaepoints in output xml file which contains x,y points etc. & when i try to change something in SIFT code it does not allows me to change any thing as it is read only (as i have added library files like libsift). So can any one help me to how to get more point of interest means 3000 or 4000 x & y points in xml file. Thank you.

Posted 14-Nov-12 7:56am

maheshpardeshi

Add a Solution

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Christian Graus · Answer 1 · 2012-11-14T07:58:00

Solution 1

It seems to me that more points of interest come from more data. How else could it work ? You've posted a lot of text, and no code, it's pretty hard to follow, but if you want help tweaking your algorithm b.c you think you have more meaningful data and you're not finding it, we'd need examples, and code. If you just want more hits, you need more data.

Posted 14-Nov-12 7:58am

Christian Graus

Comments

maheshpardeshi 14-Nov-12 14:19pm

thanks Christian for replay,as there is lots of classes in project & lots of code so not possible to paste code here you can download it from http://www.nowozin.net/sebastian/tu-berlin-2006/autopano-sift/ & i have to give my fix images as input so those i will give any image as input it should give me more points as Point of interest.actually there are lacks of pixels in my image but it is giving only 1000 as point of interest so it is difficult to detect the same object in different image.

Christian Graus 14-Nov-12 14:20pm

I'm not sure I follow all of that, but if you can't post some code and some examples of data you expect to hit that misses, I'm not sure how anyone can help you