1
$\begingroup$

My project is Face Authentication.

System Description: My input is only one image (which was taken when the user logins for the first time) and using that image system should authenticate whenever the user logins to the application. The authentication images may differ from the first input image like -- different illumination conditions, different distance from camera and -10 to 10 degrees variation in pose. The camera used is same (ex: ipad) for all cases.

1) Authentication images are stored each time the user logins. How to make use of these images to enhance the accuracy of the system??

2) When a new image comes, I need to select the closest image(s) (and not all stored images) from the image repository and use for authenticate to reduce the time. How to label an image based on illumination/distance from camera automatically??

3) How should I make my system to perform decently for changes in illumination and distance from camera??

Please, can anyone suggest me good alogirthm/papers/opensource-codes for my above questions??

Though it sounds like a research project, I would be extremely grateful if I get any response from someone.

$\endgroup$
3
  • 1
    $\begingroup$ Welcome to Signal Processing! The project you're working on is indeed something the community here can help you with. But, it is also a very big task tackling a lot of potential problems, solvable with more than one approach. It would help if you told us what you tried, what you found in your preliminary research and/or what ideas you had. The more effort you put in your questions, the more you motivate the community to give you (good) answers. $\endgroup$
    – penelope
    Oct 23, 2012 at 8:06
  • $\begingroup$ I have used OpenCV's Face Recognition API, but my systems environment has more variation and I am not satisfied with the accuracy of the API. So am looking for a better algorithm, any suggestions on this? Regardding different background, what I mean is different lighting(day,night,evening and different light shades). And your views on camera distance if any? $\endgroup$ Oct 26, 2012 at 12:44
  • $\begingroup$ @user1317087 You should edit your question and add any additional information to the question body instead of posting them in the comment section. It's much easier to read the question if all the information is in the same place :) $\endgroup$
    – penelope
    Oct 26, 2012 at 13:13

1 Answer 1

2
$\begingroup$

Here is one way to set up the project:

Rather than analysing the difference between two pictures, try analysing the pictures themselves. For example by trying to identify charactaristics of people that make them unique.

Once you do this once for the base image you can accept a login if the result of the new pic is sufficiently close to the baseline.

After you get multiple pictures you can probably get a more accurate baseline and even a confidence band.

My guess is that you should try to deal with it in a way that lighting and distance will not have much effect, so focus on ratios etc. Think about the distance between the ears compared to the distance from nose to lips or the number of rinkles on a persons forehead.

$\endgroup$
1
  • $\begingroup$ I have used OpenCV's Face Recognition API, but my systems environment has more variation and I am not satisfied with the accuracy of the API. So am looking for a better algorithm, any suggestions on this? Regardding different background, what I mean is different lighting(day,night,evening and different light shades). And your views on camera distance if any? $\endgroup$ Oct 26, 2012 at 12:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.