digiKam › digikam-devel

GSOC 2013 Computational Photography Proposal

classic Classic list List threaded Threaded
♦
♦
 4 messages Options
Siddharth
Reply | Threaded
Open this post in threaded view
♦
♦
|

GSOC 2013 Computational Photography Proposal

Siddharth
Hi,

I am currently pursuing MS by Research in the field of computer vision and image processing at IIIT- Hyderabad, India. I am interested in working for KDE/Digikam this summer in a GSoC project.

Some of my own ideas:

a) Interactive Poisson Image Editing

Image editing tasks concern either global changes (color/intensity corrections, filters, deformations) or local changes concerned to a selection. Here we are interested in achieving local changes, ones that are restricted to a region manually selected (ROI), in a seamless and effortless manner. The extent of the changes ranges from slight distortions to complete replacement by novel content. Examples:Inserting objects, Color Transfer, Feature Exchange, Texture Flattening, Local illumination changes, etc.


b) Color2Gray

Visually important image features often disappear when color images are converted to grayscale. This algorithm reduces such losses by attempting to preserve the salient features of the color image. The Color2Gray results offer viewers salient information missing from previous grayscale image creation methods.


c) Domain Transform for Edge-Aware Image Processing (Non-Photorealistic Animation and Rendering)

The processing involves high-quality edge-preserving filtering of images (better than bilateral filter). The filter is applied on several image processing tasks including edge-preserving smoothing, Depth-of-field effects, stylization, detail enhancement, edge enhancement and gray/color pencil sketch. 


What are your views about this? 

Best Regards,
Siddharth

--
Live as if you were to die tomorrow. Learn as if you were to live forever - M K Gandhi

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel
Gilles Caulier-4
Reply | Threaded
Open this post in threaded view
♦
♦
|

Re: GSOC 2013 Computational Photography Proposal

Gilles Caulier-4
Hi,

I think b) proposal is very interresting. In fact it fully relevant on GImc project which is listed in official projects list :


If you take a look to GMic announcement for last release 1.5.5.1 of library, b) is already implemented :


Sorry this announcement is in French. Use google translations to switch in English.

The advantage to use Gmic is to be able to use in the future a huge colection of algorithms to play with images.

Best

Gilles Caulier


2013/4/17 Siddharth <[hidden email]>
Hi,

I am currently pursuing MS by Research in the field of computer vision and image processing at IIIT- Hyderabad, India. I am interested in working for KDE/Digikam this summer in a GSoC project.

Some of my own ideas:

a) Interactive Poisson Image Editing

Image editing tasks concern either global changes (color/intensity corrections, filters, deformations) or local changes concerned to a selection. Here we are interested in achieving local changes, ones that are restricted to a region manually selected (ROI), in a seamless and effortless manner. The extent of the changes ranges from slight distortions to complete replacement by novel content. Examples:Inserting objects, Color Transfer, Feature Exchange, Texture Flattening, Local illumination changes, etc.


b) Color2Gray

Visually important image features often disappear when color images are converted to grayscale. This algorithm reduces such losses by attempting to preserve the salient features of the color image. The Color2Gray results offer viewers salient information missing from previous grayscale image creation methods.


c) Domain Transform for Edge-Aware Image Processing (Non-Photorealistic Animation and Rendering)

The processing involves high-quality edge-preserving filtering of images (better than bilateral filter). The filter is applied on several image processing tasks including edge-preserving smoothing, Depth-of-field effects, stylization, detail enhancement, edge enhancement and gray/color pencil sketch. 


What are your views about this? 

Best Regards,
Siddharth

--
Live as if you were to die tomorrow. Learn as if you were to live forever - M K Gandhi


_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel
Siddharth
Reply | Threaded
Open this post in threaded view
♦
♦
|

Re: GSOC 2013 Computational Photography Proposal

Siddharth
Hi,

Are some of the algorithms in Gmic already ported to Digikam?

I was thinking of implementing the suggested techniques with the help of OpenCV library. 

Best Regards,
Siddharth


On Wed, Apr 17, 2013 at 7:31 PM, Gilles Caulier <[hidden email]> wrote:
Hi,

I think b) proposal is very interresting. In fact it fully relevant on GImc project which is listed in official projects list :


If you take a look to GMic announcement for last release 1.5.5.1 of library, b) is already implemented :


Sorry this announcement is in French. Use google translations to switch in English.

The advantage to use Gmic is to be able to use in the future a huge colection of algorithms to play with images.

Best

Gilles Caulier


2013/4/17 Siddharth <[hidden email]>
Hi,

I am currently pursuing MS by Research in the field of computer vision and image processing at IIIT- Hyderabad, India. I am interested in working for KDE/Digikam this summer in a GSoC project.

Some of my own ideas:

a) Interactive Poisson Image Editing

Image editing tasks concern either global changes (color/intensity corrections, filters, deformations) or local changes concerned to a selection. Here we are interested in achieving local changes, ones that are restricted to a region manually selected (ROI), in a seamless and effortless manner. The extent of the changes ranges from slight distortions to complete replacement by novel content. Examples:Inserting objects, Color Transfer, Feature Exchange, Texture Flattening, Local illumination changes, etc.


b) Color2Gray

Visually important image features often disappear when color images are converted to grayscale. This algorithm reduces such losses by attempting to preserve the salient features of the color image. The Color2Gray results offer viewers salient information missing from previous grayscale image creation methods.


c) Domain Transform for Edge-Aware Image Processing (Non-Photorealistic Animation and Rendering)

The processing involves high-quality edge-preserving filtering of images (better than bilateral filter). The filter is applied on several image processing tasks including edge-preserving smoothing, Depth-of-field effects, stylization, detail enhancement, edge enhancement and gray/color pencil sketch. 


What are your views about this? 

Best Regards,
Siddharth

--
Live as if you were to die tomorrow. Learn as if you were to live forever - M K Gandhi




--
Live as if you were to die tomorrow. Learn as if you were to live forever - M K Gandhi

_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel
Gilles Caulier-4
Reply | Threaded
Open this post in threaded view
♦
♦
|

Re: GSOC 2013 Computational Photography Proposal

Gilles Caulier-4
In digiKam we use old version of GMic library named CImg, to use Greystoration algorithm (Restoration and Inpainting tool)

CImg is not maintained now and Greystoration have been moved to GMic.

The goal of this project is to port CImg interface to GMic, including Greystoration tools based in Image Editor, and to open to new feature as your b) proposal (and more in the future)

Gilles Caulier


2013/4/18 Siddharth <[hidden email]>
Hi,

Are some of the algorithms in Gmic already ported to Digikam?

I was thinking of implementing the suggested techniques with the help of OpenCV library. 

Best Regards,
Siddharth


On Wed, Apr 17, 2013 at 7:31 PM, Gilles Caulier <[hidden email]> wrote:
Hi,

I think b) proposal is very interresting. In fact it fully relevant on GImc project which is listed in official projects list :


If you take a look to GMic announcement for last release 1.5.5.1 of library, b) is already implemented :


Sorry this announcement is in French. Use google translations to switch in English.

The advantage to use Gmic is to be able to use in the future a huge colection of algorithms to play with images.

Best

Gilles Caulier


2013/4/17 Siddharth <[hidden email]>
Hi,

I am currently pursuing MS by Research in the field of computer vision and image processing at IIIT- Hyderabad, India. I am interested in working for KDE/Digikam this summer in a GSoC project.

Some of my own ideas:

a) Interactive Poisson Image Editing

Image editing tasks concern either global changes (color/intensity corrections, filters, deformations) or local changes concerned to a selection. Here we are interested in achieving local changes, ones that are restricted to a region manually selected (ROI), in a seamless and effortless manner. The extent of the changes ranges from slight distortions to complete replacement by novel content. Examples:Inserting objects, Color Transfer, Feature Exchange, Texture Flattening, Local illumination changes, etc.


b) Color2Gray

Visually important image features often disappear when color images are converted to grayscale. This algorithm reduces such losses by attempting to preserve the salient features of the color image. The Color2Gray results offer viewers salient information missing from previous grayscale image creation methods.


c) Domain Transform for Edge-Aware Image Processing (Non-Photorealistic Animation and Rendering)

The processing involves high-quality edge-preserving filtering of images (better than bilateral filter). The filter is applied on several image processing tasks including edge-preserving smoothing, Depth-of-field effects, stylization, detail enhancement, edge enhancement and gray/color pencil sketch. 


What are your views about this? 

Best Regards,
Siddharth

--
Live as if you were to die tomorrow. Learn as if you were to live forever - M K Gandhi




--
Live as if you were to die tomorrow. Learn as if you were to live forever - M K Gandhi


_______________________________________________
Digikam-devel mailing list
[hidden email]
https://mail.kde.org/mailman/listinfo/digikam-devel
Free forum by Nabble Edit this page