[Digikam-devel] GSoC Introduction: Aniket Handa

Mon Apr 2 11:47:14 BST 2012

Hi everyone,

During the Summer of KDE last year, I had implemented HMM face recognition
as a part of the libface library (guided by Alex and Marcel). But the
problem was scaling it by addition of new faces. The model parameters had
to be regenerated every time a new face was added and the parameters
changed accordingly. This is actually not very feasible method.

I have done an extensive study on face detection/recognition algorithms and
also worked on improving the existing face detection algorithms in libface
to make them scale, illumination and pose invariant. I am currently not in
college anymore so cannot apply for GSoC this year. But I would like to
work on the face recognition part with someone as this is a feature that
has the most demand. Any other ideas/algorithms for a scalable and
efficient face recognition algorithm can also be looked into in detail.

Thanks,
Amey

On Mon, Apr 2, 2012 at 4:06 PM, Ananta Palani <anantapalani at gmail.com>wrote:

> Hi Aniket,
>
> I think you could consider it, but be sure to read papers by other authors
> to see if the method is actually as good as the authors describe. Original
> authors of a method often show their method to be better than the
> competition (otherwise they wouldn't publish!), but if another author
> extends a given method, or does a review of all available methods, you can
> often discover whether the original claims are justified (you can usually
> find reviews / extensions by looking at articles that cite the original
> paper).
>
> From what I remember laplacianfaces is a good algorithm, but is sometimes
> inconsistent in its quality. There is also a 2d-laplacianfaces that
> performs even better, I believe. I can find the paper if you are interested.
>
> Also, compare the computation time between fisherfaces and laplacianfaces
> to help you decide which to implement.
>
> There's also no reason you couldn't implement both methods, if you had
> time!
>
> Best,
> -Ananta
>
>
> On Fri, Mar 23, 2012 at 9:58 PM, Aniket Handa <atneik at gmail.com> wrote:
>
>> Hi all!
>>
>> Should we consider LaplacianFaces for face recognition, because some
>> papers[1] suggest it gives less false positives as compared to
>> Fisherface/LDA and PCA. Or are we fine with FisherFace?
>>
>> Regards,
>> Aniket
>>
>> Attached:
>> [1] Xiaofei He;   Shuicheng Yan;   Yuxiao Hu;   Niyogi, P.;
>> Hong-Jiang Zhang: "Face recognition using Laplacianfaces" in Pattern
>> Analysis and Machine Intelligence, IEEE Transactions, March 2005
>>
>>
>> On Mon, Mar 19, 2012 at 10:42 PM, Ananta Palani <anantapalani at gmail.com>
>> wrote:
>> > I don't remember any off-hand, but I do remember they involved haar
>> wavelets
>> > and Gabor transforms. Also, I don't think they are very accurate without
>> > video input, but perhaps once sufficient images are tagged as belonging
>> to a
>> > given individual, it may be possible for the algorithm to determine the
>> > expression much easier.
>> >
>> > -Ananta
>> >
>> >
>> > On Mon, Mar 19, 2012 at 3:28 PM, Francesco Riosa <
>> francesco at pnpitalia.it>
>> > wrote:
>> >>
>> >>
>> >> Out of interest, do you know of algorithms able to extract facial
>> >> expressions #1 ?
>> >>
>> >> #1 http://en.wikipedia.org/wiki/Facial_Action_Coding_System
>> >>
>> >> Il 17/03/2012 18:12, Ananta Palani ha scritto:
>> >>>
>> >>> Hi Aniket,
>> >>>
>> >>> I'm not in charge of this particular area of digiKam, but here are
>> some
>> >>> links you can start looking into to get familiar with using OpenCV and
>> >>> performing facial recognition, as well as descriptions and papers for
>> >>> various algorithms. The current algorithm (eigenfaces) used in digiKam
>> >>> would not be very good with real-world images (even if it worked
>> >>> properly). One of the best (if not the best) algorithm available would
>> >>> be the Fisherfaces or Linear Discriminant Analysis (LDA) method. You
>> can
>> >>> read a nice summary and analysis here:
>> >>>
>> >>> http://www.bytefish.de/blog/fisherfaces
>> >>>
>> >>> Here are some good summaries of various algorithms that are available
>> >>> for further comparison:
>> >>>
>> >>> http://opencv.willowgarage.com/wiki/FaceRecognition
>> >>> http://www.face-rec.org/algorithms/
>> >>>
>> >>> I believe you have to apply and be accepted to the GSoC program before
>> >>> you can actually be work on GSoC projects, but someone else will
>> >>> probably contact you about that (or info might be on the GSoC
>> website?).
>> >>>
>> >>> Best,
>> >>> -Ananta
>> >>>
>> >>>
>> >>> On Sat, Mar 17, 2012 at 2:48 PM, Aniket Handa <atneik at gmail.com
>> >>> <mailto:atneik at gmail.com>> wrote:
>> >>>
>> >>>    Hello there,
>> >>>
>> >>>    My name is Aniket Handa, currently enrolled in Jaypee Institute of
>> >>>    Information Technology, Noida, INDIA pursing B.Tech-M.Tech Dual
>> >>>    program in Computer Science & Engineering. My interests range from
>> >>>    Computer Vision, Computer Graphics to developing Android Apps. I
>> am a
>> >>>    firm believer of FOSS.
>> >>>
>> >>>    I am particularly interested in "Facial Recognition" partially due
>> to
>> >>>    its high demand (Bug 271679: 492 votes) and partially due to my
>> >>>    interests in vision. I saw that this Idea was also in GSoC 2010, so
>> >>>    that puts up questions like: was it taken by some student? If so,
>> were
>> >>>    there some problems?
>> >>>
>> >>>    I am currently looking more about the project and will get back to
>> you
>> >>>    soon. Looking forward for being a valuable part of the community.
>> >>>
>> >>>    Regards,
>> >>>    Aniket
>> >
>> >
>> >
>> > _______________________________________________
>> > Digikam-devel mailing list
>> > Digikam-devel at kde.org
>> > https://mail.kde.org/mailman/listinfo/digikam-devel
>> >
>>
>>
>>
>> --
>> Aniket Handa
>> Site: http://atneik.com
>>
>> _______________________________________________
>> Digikam-devel mailing list
>> Digikam-devel at kde.org
>> https://mail.kde.org/mailman/listinfo/digikam-devel
>>
>>
>
> _______________________________________________
> Digikam-devel mailing list
> Digikam-devel at kde.org
> https://mail.kde.org/mailman/listinfo/digikam-devel
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.kde.org/pipermail/digikam-devel/attachments/20120402/7df2c883/attachment.html>