GSoC Introduction: Aniket Handa

[Aniket Handa]

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
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Ananta Palani]

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 <[hidden email]> 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
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Aniket Handa]

Thanks a lot Ananta. Couldn't have got better links. I am used to
OpenCV and moreover currently bytefish seems to be working on LDA, so
gotta test that around. But I'm pretty much new to KDE, I suppose that
should be a problem.

Cheers!
Aniket

On Sat, Mar 17, 2012 at 10:42 PM, Ananta Palani <[hidden email]> wrote:

> 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 <[hidden email]> 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
>> [hidden email]
>> https://mail.kde.org/mailman/listinfo/digikam-devel
>
>
>
> _______________________________________________
> Digikam-devel mailing list
> [hidden email]
> https://mail.kde.org/mailman/listinfo/digikam-devel
>

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Ananta Palani]

You're very welcome. I hope you will be able to work on this as it is a very widely requested feature (as you observed). I take it you meant to say "shouldn't" because being new to KDE won't be much of a problem. Once you get your build environment set up, the hard part will be implementing the algorithm. Retrieving image data is something done very frequently by digiKam components and whoever leads you will be able to direct you very well.

Best,
-Ananta

On Sat, Mar 17, 2012 at 5:32 PM, Aniket Handa <[hidden email]> wrote:

Thanks a lot Ananta. Couldn't have got better links. I am used to
OpenCV and moreover currently bytefish seems to be working on LDA, so
gotta test that around. But I'm pretty much new to KDE, I suppose that
should be a problem.

Cheers!
Aniket

On Sat, Mar 17, 2012 at 10:42 PM, Ananta Palani <[hidden email]> wrote:
> 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 <[hidden email]> 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
>> [hidden email]
>> https://mail.kde.org/mailman/listinfo/digikam-devel
>
>
>
> _______________________________________________
> Digikam-devel mailing list
> [hidden email]
> https://mail.kde.org/mailman/listinfo/digikam-devel
>
_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Gilles Caulier-4]

Marcel Wiesweg and Alex Jironkin are in charge to Face recognition
project. They can guide you in-deep...

Gilles Caulier

2012/3/17 Ananta Palani <[hidden email]>:

> You're very welcome. I hope you will be able to work on this as it is a very
> widely requested feature (as you observed). I take it you meant to say
> "shouldn't" because being new to KDE won't be much of a problem. Once you
> get your build environment set up, the hard part will be implementing the
> algorithm. Retrieving image data is something done very frequently by
> digiKam components and whoever leads you will be able to direct you very
> well.
>
> Best,
> -Ananta
>
>
> On Sat, Mar 17, 2012 at 5:32 PM, Aniket Handa <[hidden email]> wrote:
>>
>> Thanks a lot Ananta. Couldn't have got better links. I am used to
>> OpenCV and moreover currently bytefish seems to be working on LDA, so
>> gotta test that around. But I'm pretty much new to KDE, I suppose that
>> should be a problem.
>>
>> Cheers!
>> Aniket
>>
>> On Sat, Mar 17, 2012 at 10:42 PM, Ananta Palani <[hidden email]>
>> wrote:
>> > 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 <[hidden email]> 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
>> >> [hidden email]
>> >> https://mail.kde.org/mailman/listinfo/digikam-devel
>> >
>> >
>> >
>> > _______________________________________________
>> > Digikam-devel mailing list
>> > [hidden email]
>> > https://mail.kde.org/mailman/listinfo/digikam-devel
>> >
>> _______________________________________________
>> Digikam-devel mailing list
>> [hidden email]
>> https://mail.kde.org/mailman/listinfo/digikam-devel
>
>
>
> _______________________________________________
> Digikam-devel mailing list
> [hidden email]
> https://mail.kde.org/mailman/listinfo/digikam-devel
>

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Francesco Riosa]

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 <[hidden email]
> <mailto:[hidden email]>> 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
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Ananta Palani]

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 <[hidden email]> 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 <[hidden email]

<mailto:[hidden email]>> 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
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Aniket Handa]

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 <[hidden email]> 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 <[hidden email]>
> 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 <[hidden email]
>>> <mailto:[hidden email]>> 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
> [hidden email]
> https://mail.kde.org/mailman/listinfo/digikam-devel
>

--
Aniket Handa
Site: http://atneik.com

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Ananta Palani]

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 <[hidden email]> 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 <[hidden email]> 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 <[hidden email]>
> 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 <[hidden email]
>>> <mailto:[hidden email]>> 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
> [hidden email]
> https://mail.kde.org/mailman/listinfo/digikam-devel
>

--
Aniket Handa
Site: http://atneik.com

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Amey Dharwadker]

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 <[hidden email]> 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 <[hidden email]> 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 <[hidden email]> 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 <[hidden email]>
> 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 <[hidden email]
>>> <mailto:[hidden email]>> 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
> [hidden email]
> https://mail.kde.org/mailman/listinfo/digikam-devel
>

--
Aniket Handa
Site: http://atneik.com

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[Aniket Handa]

Greetings Ananta,

I am constantly searching for a good comparative study on face
recognition which we could actually trust and use. A rather old but
useful one was " Face Recognition: A Literature Survey W. ZHAO, R.
CHELLAPPA, P. J. PHILLIPS, A. ROSENFELD, 2003"(Cited by 3.5k+). It
basically gives a good analysis on HMM, EigenFaces, FisherFaces and
others.

Now, if talk about FisherFaces vs LaplacianFaces; I could not find a
comparison which we should consider blindly. There was one
"Two-dimensional Laplacianfaces method for face recognition by Ben
Niua, Qiang Yangb, Simon Chi Keung Shiua, Sankar Kumar Palc". Here the
authors shows some good memory, time (training + testing) analysis of
FisherFaces, EigenFace and LaplacianFaces with their 2D versions on
some good datasets. But it isn't popular. So, the best idea might be
to give them all (whose codes are available) a quick run and see if
our analysis matchs up with that of papers.

I have uploaded my proposal on google-melange. I request you to give
it a read and put in some comments. Thanks!

Regards,
Aniket
_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

[alexjironkin]

I think its good and I don't have anything else to add.

Good luck.

Alex

On 2 Apr 2012 21:19, "Aniket Handa" <[hidden email]> wrote:

Greetings Ananta,

I am constantly searching for a good comparative study on face
recognition which we could actually trust and use. A rather old but
useful one was " Face Recognition: A Literature Survey W. ZHAO, R.
CHELLAPPA, P. J. PHILLIPS, A. ROSENFELD, 2003"(Cited by 3.5k+). It
basically gives a good analysis on HMM, EigenFaces, FisherFaces and
others.

Now, if talk about FisherFaces vs LaplacianFaces; I could not find a
comparison which we should consider blindly. There was one
"Two-dimensional Laplacianfaces method for face recognition by Ben
Niua, Qiang Yangb, Simon Chi Keung Shiua, Sankar Kumar Palc". Here the
authors shows some good memory, time (training + testing) analysis of
FisherFaces, EigenFace and LaplacianFaces with their 2D versions on
some good datasets. But it isn't popular. So, the best idea might be
to give them all (whose codes are available) a quick run and see if
our analysis matchs up with that of papers.

I have uploaded my proposal on google-melange. I request you to give
it a read and put in some comments. Thanks!

Regards,
Aniket
_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel