Hi all, I am wondering if you guys know any paper or book chapter discussing optimal linear prediction for 2D or more specifically for image processing? I tried to look for it in the library in my university but could not find it. Thank you.
optimal linear prediction in image processing?
Started by ●April 11, 2010
Reply by ●April 11, 20102010-04-11
On 11 apr, 22:32, MBALOVER <mbalov...@gmail.com> wrote:> Hi all, > > I am wondering if you guys know any paper or book chapter discussing > optimal linear prediction for 2D or more specifically for image > processing? > > I tried to look for it in the library in my university but could not > find it.'Linear prediction' could mean just about anything in the context of image processing. You might want to narrow the search a bit, by hinting at the application. And you might want to ask at comp.soft-sys.matlab (I have added CSSM to the follow-up), as there are a couple of regulars there who know their image processing. Rune
Reply by ●April 11, 20102010-04-11
MBALOVER wrote:> Hi all, > > I am wondering if you guys know any paper or book chapter discussing > optimal linear prediction for 2D or more specifically for image > processing?Plane prediction is very common in video processing: A | B ------- C | X X predicted = B + C - A Multidimensional LPC is known bad problem; I don't know if anybody got anything useful out of it. Vladimir Vassilevsky DSP and Mixed Signal Design Consultant http://www.abvolt.com
Reply by ●April 12, 20102010-04-12
On Apr 12, 7:26�am, Vladimir Vassilevsky <nos...@nowhere.com> wrote:> MBALOVER wrote: > > Hi all, > > > I am wondering if you guys know any paper or book chapter discussing > > optimal linear prediction for 2D or more specifically for image > > processing? > > Plane prediction is very common in video processing: > > � A | B > ------- > � C | X > > X predicted = B + C - A > > Multidimensional LPC is known bad problem; I don't know if anybody got > anything useful out of it. > > Vladimir Vassilevsky > DSP and Mixed Signal Design Consultanthttp://www.abvolt.comThe prediction you mention is like the MV prediction in video coding. Recently, I am interested in object tracking. I know that Kalman filter are used in object tracking. I am not familiar with it very much, but I learn there is a prediction step in the procedure. The title of this thread is too board. There are too many things that is regarded as image processing such as denoise, segmentation and so on. Jogging
Reply by ●April 12, 20102010-04-12
On Apr 11, 2:32�pm, MBALOVER <mbalov...@gmail.com> wrote:> Hi all, > > I am wondering if you guys know any paper or book chapter discussing > optimal linear prediction for 2D or more specifically for image > processing? > > I tried to look for it in the library in my university but could not > find it. > > Thank you."Linear prediction" in 1D signal processing almost always refers to Autoregressive (AR) signal models. For 2D AR, google ' "autoregression" "image processing" .'
Reply by ●April 12, 20102010-04-12
MBALOVER wrote:> Hi all, > > I am wondering if you guys know any paper or book chapter discussing > optimal linear prediction for 2D or more specifically for image > processing?I'm not sure that there is a single source that discusses all available linear predictors, but there are a couple of classical results. - depending on your definition of optimality. For example, if "optimality" is defined in terms of optimal decorrelation, then the answer is the KLT (the operator that diagonalizes the correlation matrix). Then again, you have more classical results that the KLT is, for stationary (position-independent) processes just the Fourier transformation. A couple of predictors are discussed in the classical "Digital pictures: representation, compression, and standards" by Netravali et al. Probably a bit outdated, but still a good introduction. Greetings, Thomas
Reply by ●April 12, 20102010-04-12
On Apr 12, 6:26�am, Vladimir Vassilevsky <nos...@nowhere.com> wrote:> MBALOVER wrote: > > I am wondering if you guys know any paper or book chapter discussing > > optimal linear prediction for 2D or more specifically for image > > processing? > > Plane prediction is very common in video processing: > > � A | B > ------- > � C | X > > X predicted = B + C - AVery simple non-linear predictors can be better than even the best linear predictors. For example, B + C - median(A,B,C) may be better than the B + C - A just mentioned, and has the advantage that the prediction is always "in-range" (violation of which could be inconvenient). There are alternate formulations that may look quite different from " B + C - median(A, B, C) " but are in fact equivalent. This particular predictor has been rediscovered at least 3 times. James
Reply by ●April 13, 20102010-04-13
On Apr 12, 8:32�am, MBALOVER <mbalov...@gmail.com> wrote:> Hi all, > > I am wondering if you guys know any paper or book chapter discussing > optimal linear prediction for 2D or more specifically for image > processing? > > I tried to look for it in the library in my university but could not > find it. > > Thank you.The 1D theory should carry through for filtering,smoothing and prediction. Should be a huge literature. Hardy
