Acoustic contrast factor: Difference between revisions
en>Yobot m autotagging+genfixes, added Empty section (1) tag using AWB (6870) |
en>Hhhippo +unref, -empty sections |
||
| Line 1: | Line 1: | ||
[[File:Image restoration (motion blur, Wiener filtering).png|thumb|350px|From left: Original image, blurred image, image deblurred using Wiener deconvolution.]] | |||
In [[mathematics]], '''Wiener deconvolution''' is an application of the [[Wiener filter]] to the [[noise]] problems inherent in [[deconvolution]]. It works in the [[frequency domain]], attempting to minimize the impact of deconvoluted noise at frequencies which have a poor [[signal-to-noise ratio]]. | |||
The Wiener deconvolution method has widespread use in [[image]] deconvolution applications, as the frequency spectrum of most visual images is fairly well behaved and may be estimated easily. | |||
Wiener deconvolution is named after [[Norbert Wiener]]. | |||
== Definition == | |||
Given a system: | |||
:<math>\ y(t) = h(t)*x(t) + n(t)</math> | |||
where <math>*</math> denotes [[convolution]] and: | |||
*<math>\ x(t)</math> is some input signal (unknown) at time <math>\ t </math>. | |||
*<math>\ h(t)</math> is the known [[impulse response]] of a [[LTI system theory|linear time-invariant]] system | |||
*<math>\ n(t)</math> is some unknown additive noise, [[statistical independence|independent]] of <math>\ x(t)</math> | |||
*<math>\ y(t)</math> is our observed signal | |||
Our goal is to find some <math>\ g(t)</math> so that we can estimate <math>\ x(t)</math> as follows: | |||
:<math>\ \hat{x}(t) = g(t)*y(t)</math> | |||
where <math>\ \hat{x}(t)</math> is an estimate of <math>\ x(t)</math> that minimizes the [[mean square error]]. | |||
The Wiener deconvolution filter provides such a <math>\ g(t)</math>. The filter is most easily described in the [[frequency domain]]: | |||
:<math>\ G(f) = \frac{H^*(f)S(f)}{ |H(f)|^2 S(f) + N(f) }</math> | |||
where: | |||
* <math>\ G(f)</math> and <math>\ H(f)</math> are the [[Fourier transform]]s of <math>\ g</math> and <math>\ h</math>, respectively at frequency <math>\ f </math>. | |||
* <math>\ S(f)</math> is the mean [[power spectral density]] of the input signal <math>\ x(t)</math> | |||
* <math>\ N(f)</math> is the mean power spectral density of the noise <math>\ n(t)</math> | |||
* the superscript <math>{}^*</math> denotes [[complex conjugate|complex conjugation]]. | |||
The filtering operation may either be carried out in the time-domain, as above, or in the frequency domain: | |||
:<math>\ \hat{X}(f) = G(f)Y(f)</math> | |||
(where <math>\ \hat{X}(f)</math> is the Fourier transform of <math>\hat{x}(t)</math>) and then performing an [[inverse Fourier transform]] on <math>\ \hat{X}(f)</math> to obtain <math>\ \hat{x}(t)</math>. | |||
Note that in the case of images, the arguments <math>\ t </math> and <math>\ f </math> above become two-dimensional; however the result is the same. | |||
== Interpretation == | |||
The operation of the Wiener filter becomes apparent when the filter equation above is rewritten: | |||
:<math> | |||
\begin{align} | |||
G(f) & = \frac{1}{H(f)} \left[ \frac{ |H(f)|^2 }{ |H(f)|^2 + \frac{N(f)}{S(f)} } \right] \\ | |||
& = \frac{1}{H(f)} \left[ \frac{ |H(f)|^2 }{ |H(f)|^2 + \frac{1}{\mathrm{SNR}(f)}} \right] | |||
\end{align} | |||
</math> | |||
Here, <math>\ 1/H(f)</math> is the inverse of the original system, and <math>\ \mathrm{SNR}(f) = S(f)/N(f)</math> is the [[signal-to-noise ratio]]. When there is zero noise (i.e. infinite signal-to-noise), the term inside the square brackets equals 1, which means that the Wiener filter is simply the inverse of the system, as we might expect. However, as the noise at certain frequencies increases, the signal-to-noise ratio drops, so the term inside the square brackets also drops. This means that the Wiener filter attenuates frequencies dependent on their signal-to-noise ratio. | |||
The Wiener filter equation above requires us to know the spectral content of a typical image, and also that of the noise. Often, we do not have access to these exact quantities, but we may be in a situation where good estimates can be made. For instance, in the case of photographic images, the signal (the original image) typically has strong low frequencies and weak high frequencies, and in many cases the noise content will be relatively flat with frequency. | |||
== Derivation == | |||
As mentioned above, we want to produce an estimate of the original signal that minimizes the mean square error, which may be expressed: | |||
:<math>\ \epsilon(f) = \mathbb{E} \left| X(f) - \hat{X}(f) \right|^2</math> | |||
where <math>\ \mathbb{E}</math> denotes [[Expected value|expectation]]. | |||
If we substitute in the expression for <math>\ \hat{X}(f)</math>, the above can be rearranged to | |||
:<math> | |||
\begin{align} | |||
\epsilon(f) & = \mathbb{E} \left| X(f) - G(f)Y(f) \right|^2 \\ | |||
& = \mathbb{E} \left| X(f) - G(f) \left[ H(f)X(f) + V(f) \right] \right|^2 \\ | |||
& = \mathbb{E} \big| \left[ 1 - G(f)H(f) \right] X(f) - G(f)V(f) \big|^2 | |||
\end{align} | |||
</math> | |||
If we expand the quadratic, we get the following: | |||
:<math> | |||
\begin{align} | |||
\epsilon(f) & = \Big[ 1-G(f)H(f) \Big] \Big[ 1-G(f)H(f) \Big]^*\, \mathbb{E}|X(f)|^2 \\ | |||
& {} - \Big[ 1-G(f)H(f) \Big] G^*(f)\, \mathbb{E}\Big\{X(f)V^*(f)\Big\} \\ | |||
& {} - G(f) \Big[ 1-G(f)H(f) \Big]^*\, \mathbb{E}\Big\{V(f)X^*(f)\Big\} \\ | |||
& {} + G(f) G^*(f)\, \mathbb{E}|V(f)|^2 | |||
\end{align} | |||
</math> | |||
However, we are assuming that the noise is independent of the signal, therefore: | |||
:<math>\ \mathbb{E}\Big\{X(f)V^*(f)\Big\} = \mathbb{E}\Big\{V(f)X^*(f)\Big\} = 0</math> | |||
Also, we are defining the power spectral densities as follows: | |||
:<math>\ S(f) = \mathbb{E}|X(f)|^2</math> | |||
:<math>\ N(f) = \mathbb{E}|V(f)|^2</math> | |||
Therefore, we have: | |||
:<math> | |||
\begin{align} | |||
\epsilon(f) & = \Big[ 1-G(f)H(f) \Big]\Big[ 1-G(f)H(f) \Big]^* S(f) \\ | |||
& {} + G(f)G^*(f)N(f) | |||
\end{align} | |||
</math> | |||
To find the minimum error value, we calculate the [[Wirtinger derivatives|Wirtinger derivative]] with respect to <math>\ G(f)</math> and set it equal to zero. | |||
:<math>\ | |||
\frac{d\epsilon(f)}{dG(f)} = G^*(f)N(f) - H(f)\Big[1 - G(f)H(f)\Big]^* S(f) = 0 | |||
</math> | |||
This final equality can be rearranged to give the Wiener filter. | |||
== See also == | |||
* [[Deconvolution]] | |||
* [[Wiener filter]] | |||
* [[Point spread function]] | |||
* [[Blind deconvolution]] | |||
* [[Fourier transform]] | |||
{{Commons|File:Image restoration (motion blur, Wiener filtering).png|An example of Wiener deconvolution on motion blured image (and source codes in MATLAB/GNU Octave).}} | |||
== References == | |||
* Rafael Gonzalez, Richard Woods, and Steven Eddins. ''Digital Image Processing Using Matlab''. Prentice Hall, 2003. | |||
== External links == | |||
* [http://www.owlnet.rice.edu/~elec539/Projects99/BACH/proj2/blind/bd.html Comparison of different deconvolution methods.] | |||
* [http://cnx.org/content/m13144/latest/ Deconvolution with a Wiener filter] | |||
[[Category:Signal processing]] | |||
[[Category:Image noise reduction techniques]] | |||
[[Category:Estimation theory]] | |||
Revision as of 23:51, 23 October 2012
In mathematics, Wiener deconvolution is an application of the Wiener filter to the noise problems inherent in deconvolution. It works in the frequency domain, attempting to minimize the impact of deconvoluted noise at frequencies which have a poor signal-to-noise ratio.
The Wiener deconvolution method has widespread use in image deconvolution applications, as the frequency spectrum of most visual images is fairly well behaved and may be estimated easily.
Wiener deconvolution is named after Norbert Wiener.
Definition
Given a system:
where denotes convolution and:
- is some input signal (unknown) at time .
- is the known impulse response of a linear time-invariant system
- is some unknown additive noise, independent of
- is our observed signal
Our goal is to find some so that we can estimate as follows:
where is an estimate of that minimizes the mean square error.
The Wiener deconvolution filter provides such a . The filter is most easily described in the frequency domain:
where:
- and are the Fourier transforms of and , respectively at frequency .
- is the mean power spectral density of the input signal
- is the mean power spectral density of the noise
- the superscript denotes complex conjugation.
The filtering operation may either be carried out in the time-domain, as above, or in the frequency domain:
(where is the Fourier transform of ) and then performing an inverse Fourier transform on to obtain .
Note that in the case of images, the arguments and above become two-dimensional; however the result is the same.
Interpretation
The operation of the Wiener filter becomes apparent when the filter equation above is rewritten:
Here, is the inverse of the original system, and is the signal-to-noise ratio. When there is zero noise (i.e. infinite signal-to-noise), the term inside the square brackets equals 1, which means that the Wiener filter is simply the inverse of the system, as we might expect. However, as the noise at certain frequencies increases, the signal-to-noise ratio drops, so the term inside the square brackets also drops. This means that the Wiener filter attenuates frequencies dependent on their signal-to-noise ratio.
The Wiener filter equation above requires us to know the spectral content of a typical image, and also that of the noise. Often, we do not have access to these exact quantities, but we may be in a situation where good estimates can be made. For instance, in the case of photographic images, the signal (the original image) typically has strong low frequencies and weak high frequencies, and in many cases the noise content will be relatively flat with frequency.
Derivation
As mentioned above, we want to produce an estimate of the original signal that minimizes the mean square error, which may be expressed:
where denotes expectation.
If we substitute in the expression for , the above can be rearranged to
If we expand the quadratic, we get the following:
However, we are assuming that the noise is independent of the signal, therefore:
Also, we are defining the power spectral densities as follows:
Therefore, we have:
To find the minimum error value, we calculate the Wirtinger derivative with respect to and set it equal to zero.
This final equality can be rearranged to give the Wiener filter.
See also
Most brokers paid and post their listings at these online property categorised portals but fail to realise that there is simply extra to it. They fail to leverage on one of the vital well-liked on-line advertising and marketing tool of their marketing campaign and that is through the social media.
In case you are among the many few who've passed the grueling Actual Estate Salesperson (RES) course, congratulations. So what next? Which agency should you be a part of? Earlier than taking the plunge, you will need to choose the proper mentor who can educate you the ropes in actual estate. An excellent mentor will allow you to navigate the complex world of real property by instructing you the way to get listings, advertising and marketing methods, real estate contracts and methods to closing your deal. He will even caution you on errors to keep away from that would land you in trouble. This has been reflected within the Industrial Production reading index for prescribed drugs. In June, the reading fell to one hundred thirty from 287. Effectively if you do not, you then're simply leaving your actual property enterprise to chance. Commons for rent
Thanks to hirepropertyagent.com.sg, i've discovered myself a good agent. He did a great job promoting my property and it was bought at an excellent value." JLL appointed unique agent for the sale of 2, 4 and 6 Dunlop Street by Expression of Curiosity. Uncommon Industrial Growth inside Pandan Meals Zone space up for sale conserving you updated with the property market 3. Work @ Residence IT Solutions As property costs cool in Hong Kong and Singapore, which have lengthy been magnets for Chinese language funding, extra money is flowing to actual property markets comparable to New York, London and Sydney. Chinese language have overtaken Russians house for sale in singapore the primary time as the biggest buyers of flats in Manhattan, in response to actual estate brokers. Condominium For Lease – Tribeca by the Waterfront (D09)
Property developer and residential landlord for flats and homes for lease and sale. Most property firms share the same database of property listings in Singapore. Due to this fact it is best to solely use only ONE agent at a time. In case you approach many agents at the similar time, very likely that they'll present you the same property. A lot confusion and embarrassment will arise should you engage many brokers. One of the best, and most of the time only, strategy to discover a good property agent in Singapore is phrase-of-mouth. Ask your friends and colleagues for reference. It is very simple to provide you with a couple of candidates since a lot of the expatriates dwelling in Singapore for a long time can have several good agent contacts to guide you. Toa Payoh, Singapore Singapore 319378 Estate
This is precisely what happened to me and my husband at the moment, to not point out a very unscrupulous developer operating in a really unprofessional manner. I need to share this story with everyone here, and please pass the message round particularly among expats communities, beware while you want to purchase property developed by VicLand Pte Ltd and if developer's agent is ECG property. There was only one unit left on the market by developer, 03-09, a 3 bed room flat. On the time my husband was out of town, and initially I liked what I saw so I instructed the developer's agent and my agent we should come back with my husband in two weeks to view it once more and make a decision after ward. Complaint / Suggestions about lousy property agent Darren Ng from Dennis Wee
This bought me thinking and I started to surprise – how much does a property agent really earn? We often hear or read about sure brokers making million dollar commissions, however is that the exception or the norm? That piqued my curiosity. Like any job, those who put in time and effort will do well and rise to the top. The ethics of exhausting work apply to the true property market as nicely. For individuals who are pondering of making a career change to develop into a property agent, you should be ready to invest the trouble to do properly. Otherwise you may just add to the statistic of brokers who eventually drop out of the realtor game. Properties that do not fall within the definition of residential properties stated above are non-residential properties Web site - www.riaschool.com.sg
Ought to you are on the lookout for new properties for investment or for own stay, we offer property recommendation and search services tailored to your needs. We have represented many together with worldwide and local buyers in efficiently finishing their property purchases. We work with main builders to bring you the latest and one of the best prime properties in Singapore. We are a one-cease service that may full your property cycle from purchase to sale. Property agents for Singapore Land Authority protecting among the government colonial properties for rent. Property leases for expatriates and foreigners. Also helps expats to purchase and promote their properties as well as property investment opportunities in Singapore and China. The Restaurant Affiliation of Singapore
References
- Rafael Gonzalez, Richard Woods, and Steven Eddins. Digital Image Processing Using Matlab. Prentice Hall, 2003.