Image moments

Image moments

Used in image processing, computer vision and related fields, image moments are certain particular weighted averages ("moments") of the image pixels' intensities, or functions of those moments, usually chosen to have some attractive property or interpretation.

They are useful to describe objects after segmentation. Simple properties of the image which are found "via" image moments include area (or total intensity), its centroid, and information about its orientation.

Raw moments

For a 2-D continuous function "f"("x","y") the moment (sometimes called "raw moment") of order ("p" + "q") is defined as : M_{pq}=intlimits_{-infty}^{infty} intlimits_{-infty}^{infty} x^py^qf(x,y) ,dx, dy

for "p","q" = 0,1,2,...Adapting this to scalar (greytone) image with pixel intensities "I"("x","y"), raw image moments "Mij" are calculated by

:M_{ij} = sum_x sum_y x^i y^j I(x,y),!

In some cases, this may be calculated by considering the image as a probability density function, "i.e.", by dividing the above by

:sum_x sum_y I(x,y) ,! A uniqueness theorem (Papoulis [1991] ) states that if "f"("x","y") is piecewise continuous and has nonzero values only in a finite part of the "xy" plane, moments of all orders exist, and the moment sequence ("Mpq") is uniquely determined by "f"("x","y"). Conversely, ("Mpq") uniquely determines "f"("x","y"). In practice, the image is summarized with functions of a few lower order moments.

Examples

Simple image properties derived "via" raw moments include:
* Area (for binary images) or sum of grey level (for greytone images): "M"00
* Centroid: {ar{x}, ar{y} } = {"M"10/"M"00, "M"01/"M"00 }

Central moments

Central moments are defined as

: mu_{pq} = intlimits_{-infty}^{infty} intlimits_{-infty}^{infty} (x - ar{x})^p(y - ar{y})^q f(x,y) , dx , dy

where ar{x}=frac{M_{10{M_{00 and ar{y}=frac{M_{01{M_{00 are the components of the centroid.

If f(x, y) is a digital image, then the previous equation becomes

:mu_{pq} = sum_{x} sum_{y} (x - ar{x})^p(y - ar{y})^q f(x,y)

The central moments of order up to 3 are:

:mu_{00} = M_{00},,!:mu_{01} = 0,,!:mu_{10} = 0,,!:mu_{11} = M_{11} - ar{x} M_{01} = M_{11} - ar{y} M_{10},:mu_{20} = M_{20} - ar{x} M_{10}, :mu_{02} = M_{02} - ar{y} M_{01}, :mu_{21} = M_{21} - 2 ar{x} M_{11} - ar{y} M_{20} + 2 ar{x}^2 M_{01}, :mu_{12} = M_{12} - 2 ar{y} M_{11} - ar{x} M_{02} + 2 ar{y}^2 M_{10}, :mu_{30} = M_{30} - 3 ar{x} M_{20} + 2 ar{x}^2 M_{10}, :mu_{03} = M_{03} - 3 ar{y} M_{02} + 2 ar{y}^2 M_{01}.

It can be shown that::mu_{pq} = sum_{m}^p sum_{n}^q {pchoose m} {qchoose n}(-ar{x})^{(p-m)}(-ar{y})^{(q-n)} M_{mn}

Central moments are translational invariant.

Examples

Information about image orientation can be derived by first using the second order central moments to construct a covariance matrix.

:mu'_{20} = mu_{20} / mu_{00} = M_{20}/M_{00} - ar{x}^2:mu'_{02} = mu_{02} / mu_{00} = M_{02}/M_{00} - ar{y}^2:mu'_{11} = mu_{11} / mu_{00} = M_{11}/M_{00} - ar{x}ar{y}

The covariance matrix of the image I(x,y) is now

:operatorname{cov} [I(x,y)] = egin{bmatrix} mu'_{20} & mu'_{11} \ mu'_{11} & mu'_{02} end{bmatrix}.

The eigenvectors of this matrix correspond to the major and minor axes of the image intensity, so the orientation can thus be extracted from the angle of the eigenvector associated with the largest eigenvalue. It can be shown that this angle Θ is given by the following formula:

:Theta = frac{1}{2} arctan left( frac{2mu'_{11{mu'_{20} - mu'_{02 ight)

The eigenvalues of the covariance matrix can easily be shown to be

: lambda_i = frac{mu'_{20} + mu'_{02{2} pm frac{sqrt{4{mu'}_{11}^2 + ({mu'}_{20}-{mu'}_{02})^2 {2},

and are proportional to the squared length of the eigenvector axes. The relative difference in magnitude of the eigenvalues are thus an indication of the eccentricity of the image, or how elongated it is. The eccentricity is

: sqrt{1 - frac{lambda_2}{lambda_1.

Scale invariant moments

Moments "ηi j" where "i" + "j" ≥ 2 can be constructed to be invariant to both translation and changes in scale by dividing the corresponding central moment by the properly scaled (00)th moment, using the following formula.

:eta_{ij} = frac{mu_{ij {mu_{00}^{left(1 + frac{i+j}{2} ight),!

Rotation invariant moments

It is possible to calculate moments which are invariant under translation, changes in scale, and also "rotation". Most frequently used are the Hu set of invariant moments:

: egin{align} I_1 = & eta_{20} + eta_{02} \ I_2 = & (eta_{20} - eta_{02})^2 + (2eta_{11})^2 \ I_3 = & (eta_{30} - 3eta_{12})^2 + (3eta_{21} - eta_{03})^2 \ I_4 = & (eta_{30} + eta_{12})^2 + (eta_{21} + eta_{03})^2 \ I_5 = & (eta_{30} - 3eta_{12}) (eta_{30} + eta_{12}) [ (eta_{30} + eta_{12})^2 - 3 (eta_{21} + eta_{03})^2] + \ & (3eta_{21} - eta_{03}) (eta_{21} + eta_{03}) [ 3(eta_{30} + eta_{12})^2 - (eta_{21} + eta_{03})^2] \ I_6 = & (eta_{20} - eta_{02}) [(eta_{30} + eta_{12})^2 - (eta_{21} + eta_{03})^2] + 4eta_{11}(eta_{30} + eta_{12})(eta_{21} + eta_{03}) \ I_7 = & (3eta_{21} - eta_{03})(eta_{30} + eta_{12}) [(eta_{30} + eta_{12})^2 - 3(eta_{21} + eta_{03})^2] - \ & (eta_{30} - 3eta_{12})(eta_{21} + eta_{03}) [3(eta_{30} + eta_{12})^2 - (eta_{21} + eta_{03})^2] . end{align}

The first one, "I"1, is roughly proportional to the moment of inertia around the image's centroid, if the pixels' intensities were interpreted as physical density. The last one, "I"7, is skew invariant, which enables it to distinguish mirror images of otherwise identical images.

A general theory on deriving complete and independent sets of rotation invariants was proposed by J. Flusser and T. Suk.

External links

* [http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/OWENS/LECT2/node3.html Analysis of Binary Images] , University of Edinburgh
* [http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/SHUTLER3/CVonline_moments.html Statistical Moments] , University of Edinburgh

References

* M. K. Hu, "Visual Pattern Recognition by Moment Invariants", IRE Trans. Info. Theory, vol. IT-8, pp.179-187, 1962.

* J. Flusser: "On the Independence of Rotation Moment Invariants", Pattern Recognition, vol. 33, pp. 1405-1410, 2000.

* J. Flusser and T. Suk, "Rotation Moment Invariants for Recognition of Symmetric Objects", IEEE Trans. Image Proc., vol. 15, pp. 3784-3790, 2006.


Wikimedia Foundation. 2010.

Игры ⚽ Нужна курсовая?

Look at other dictionaries:

  • Image moment — In image processing, computer vision and related fields, an image moment is a certain particular weighted average (moment) of the image pixels intensities, or a function of such moments, usually chosen to have some attractive property or… …   Wikipedia

  • Image par résonance magnétique nucléaire — Imagerie par résonance magnétique Pour les articles homonymes, voir IRM et MRI. L imagerie par résonance magnétique nucléaire (IRM) est une technique d imagerie médicale d apparition récente (début des années 1980) permettant d avoir une vue 2D… …   Wikipédia en Français

  • Image subliminale — Message subliminal Pour les articles homonymes, voir message (homonymie). Un message subliminal est un stimulus incorporé dans un objet, conçu pour être perçu à un niveau au dessous du niveau de conscience. Des techniques subliminales ont été… …   Wikipédia en Français

  • Image du Christ — Représentation artistique de Jésus Christ Dans les bras de Joseph …   Wikipédia en Français

  • FEMME - L’image de la femme — Il n’y a pas de nu en littérature. Seul eût été capable de nous le donner Raymond Roussel si, moins intéressé par les mécanismes, il avait pu, à propos d’une femme, ne nous en tendre que l’enveloppe. Telle école ou tel moment parcelle la femme en …   Encyclopédie Universelle

  • movement-image —    by Tom Conley   The movement image is the title of the first panel of a historical diptych, Cinema 1 and Cinema 2, that classifies modes of perception and production of film from its beginnings in 1895 up to 1985. In this work and its… …   The Deleuze dictionary

  • movement-image —    by Tom Conley   The movement image is the title of the first panel of a historical diptych, Cinema 1 and Cinema 2, that classifies modes of perception and production of film from its beginnings in 1895 up to 1985. In this work and its… …   The Deleuze dictionary

  • Les Derniers Moments de Michel Lepeletier — gravure de Tardieu d après le tableau de David Artiste Jacques Louis David Année 1793 Technique …   Wikipédia en Français

  • Seventeen Moments of Spring — Infobox Film name = Seventeen Moments of Spring image size = caption = director = Tatiana Lioznova producer = writer = based on the books by Yulian Semyonov narrator = starring = Vyacheslav Tikhonov music = Mikael Tariverdiev cinematography =… …   Wikipedia

  • Shape factor (image analysis and microscopy) — Shape factors are dimensionless quantities used in image analysis and microscopy that numerically describe the shape of a particle, independent of its size. Shape factors are calculated from measured dimensions, such as diameter, chord lengths,… …   Wikipedia

Share the article and excerpts

Direct link
Do a right-click on the link above
and select “Copy Link”