Find the difference between images

2012 3 27
5 个回答
4 次查看（30 天）

0 个投票

Dear, masters in matlab & neural networks, sorry for my English. Please, advise me if it is real to develop neural network that will compare two images(original and its compressed version) and return the distortion level between them? If 'yes', what kind of network should be used? May be, someone has examples?

2 个评论
显示 无 隐藏 无

Image Analyst
Image Analyst 2012-3-27
To be clear, you mean with the compressed version once it's been decompressed.
Walter Roberson
Walter Roberson 2012-3-27
Rotated? Translated? Cropped? Resized? Or _exact_ size and image position matches?

请先登录，再进行评论。

请先登录，再回答此问题。

回答（5 个）

Geoff
Geoff 2012-3-27

2 个投票

Why wouldn't you just subtract one from the other and use some statistics like mean, variance, etc?
Greg Heath
Greg Heath 2012-4-4

1 个投票

You said that you have found a reference but have no access.
An obvious way to begin is either obtain access to the reference or obtain access to one of the authors.
To use a neural net you have to train it with typical examples of input-output vector pairs.
From what I've read so far your input is a 64-dimensional input vector obtained from columnizing an 8x8 window of a difference image and your output is a scalar measure of similarity.
The enigma here is how to calculate the MOS to use for training.
Once that is defined, you don't need the network.
Or am I missing something?
Hope this helps.
P.S. Use windows with odd numbers of pixels per edge so that the middle of the window is at a pixel location.

1 个评论
显示 -1更早的评论 隐藏 -1更早的评论

belka0011
belka0011 2012-4-5
Yes, an input is 64 - discrete cosine transformed pixels.
I think that I should use sigmoid function and will try it in nn toolbox

请先登录，再进行评论。

belka0011
belka0011 2012-3-28

0 个投票

I want to develop NN that will better in searching artifacts than PSNR.
I've found description of work with almost similar problem, but I haven't access there((
If be anyone can help me?

9 个评论
显示 7更早的评论 隐藏 7更早的评论

Walter Roberson
Walter Roberson 2012-3-28
What kind of artifacts are you referring to for your purposes?
Are you talking about weighting some differences as more important based upon surrounding context?
Image Analyst
Image Analyst 2012-3-28
Better how? What's "wrong" with PSNR? What shortcomings do you feel that it has? PSNR is a well established technique that gives a single number that is used as a quality metric for comparing an original image with one that has undergone the compression/decompression round trip. Your method will likewise give a single number. Do you plan on doing psychophysical experiments to prove your number correlates better with human perception than PSNR? Maybe you ought to read this paper first: http://spiedigitallibrary.org/jei/resource/1/jeime5/v19/i4/p043004_s1?isAuthorized=no
belka0011
belka0011 2012-3-31
thanks for the reference...but I should use neural network and find artifacts after embedding digital watermarks in image
Walter Roberson
Walter Roberson 2012-3-31
So there isn't any compression step?
Image Analyst
Image Analyst 2012-3-31
belka, but you still didn't answer my questions.
belka0011
belka0011 2012-3-31
2walter: no compression, only embedding watermarks
belka0011
belka0011 2012-3-31
2image analyst: "Your method will likewise give a single number" yes.
And, yes, I will do psychophysical experiments
Image Analyst
Image Analyst 2012-3-31
And what shortcomings do the current methods have that your method will overcome?
Walter Roberson
Walter Roberson 2012-4-1
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.5.6925&rep=rep1&type=pdf

请先登录，再进行评论。

belka0011
belka0011 2012-4-3

0 个投票

I cannot say why my idea better than PSNR, that's my scientific work...
Now I've decided to develop neural network, that will contain pairs: artifact(8x8 pixels in DCT) and coefficient(from 0 to 1, depending on it visualization).
And now new question, how better to realize it?

4 个评论
显示 2更早的评论 隐藏 2更早的评论

Image Analyst
Image Analyst 2012-4-4
Better than what? What do you have so far? I'd say the Neural Net Toolbox would be a good thing to help you realize it.
belka0011
belka0011 2012-4-4
Better for this aims, what performance function and what training function to use?
Image Analyst
Image Analyst 2012-4-4
I don't use neural nets. Sorry - I can't help.
belka0011
belka0011 2012-4-5
anyway, thanks for your answers =)

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

标签

提问:

belka0011
belka0011
2012-3-27

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by