Exact category - Revision history

en>John of Reading: Typo/general fixing, replaced: vice-versa → vice versa using AWB

2015-01-03T19:58:05Z

Typo/general fixing, replaced: vice-versa → vice versa using AWB

← Older revision		Revision as of 21:58, 3 January 2015
Line 1:		Line 1:
	~~'''Mean shift'''~~ is ~~a [[non-parametric]] [[feature space\|feature-space]] analysis technique, a so-called [[mode seeking]] algorithm.<ref name="PAMI95">{{cite journal~~		Andrew Simcox is the title his parents gave him and he totally enjoys this name. Playing badminton is a thing that he is totally addicted to. Her family lives in Alaska but her spouse wants them to transfer. I am an invoicing officer and I'll be promoted quickly.<br><br>My web-site ... free psychic reading ([http://breenq.com/index.php?do=/profile-1144/info/ go to this web-site])
	~~\| last = Cheng~~
	~~\| first = Yizong~~
	~~\| authorlink =~~
	\| title ~~= Mean Shift, Mode Seeking,~~ and ~~Clustering~~
	~~\| journal = IEEE Transactions on Pattern Analysis and Machine Intelligence~~
	~~\| volume = 17~~
	~~\| issue = 8~~
	~~\| pages = 790–799~~
	~~\| publisher = IEEE~~
	~~\| location =~~
	~~\| date = August 1995~~
	~~\| url =~~
	~~\| doi = 10.1109/34.400568~~
	~~\| id =~~
	~~\| accessdate = }}</ref> Application domains include [[cluster analysis]] in [[computer vision]] and [[image processing]].<ref name="PAMI02">{{cite journal~~
	~~\| last = Comaniciu~~
	~~\| first = Dorin~~
	~~\| authorlink =~~
	~~\| coauthors = Peter Meer~~
	~~\| title = Mean Shift: A Robust Approach Toward Feature Space Analysis~~
	~~\| journal = IEEE Transactions on Pattern Analysis and Machine Intelligence~~
	~~\| volume = 24~~
	~~\| issue = 5~~
	~~\| pages = 603–619~~
	~~\| publisher = IEEE~~
	~~\| location =~~
	~~\| date = May 2002~~
	~~\| url =~~
	~~\| doi = 10.1109/34.1000236~~
	~~\| id =~~
	~~\| accessdate = 2008-02-29}}</ref>~~

	~~== History ==~~
	~~The mean shift procedure was originally presented in 1975 by Fukunaga and Hostetler.<ref~~ name~~="Fukunaga">{{cite journal~~
	~~\| last = Fukunaga~~
	~~\| first = Keinosuke~~
	~~\| authorlink =~~
	~~\| coauthors = Larry D~~. ~~Hostetler~~
	~~\| title = The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition~~
	~~\| journal = IEEE Transactions on Information Theory~~
	~~\| volume = 21~~
	~~\| issue = 1~~
	~~\| pages = 32–40~~
	~~\| publisher = IEEE~~
	~~\| location =~~
	~~\| date = January 1975~~
	~~\| url = http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1055330~~
	~~\| doi =10.1109/TIT.1975.1055330~~
	~~\| id =~~
	~~\| accessdate = 2008-02-29}}</ref>~~

	~~== Overview ==~~
	~~Mean shift~~ is a ~~procedure for locating the maxima of a [[density function]] given discrete data sampled from~~ that ~~function.<ref name="PAMI95" /> It is useful for detecting the [[Mode (statistics)\|mode]]s of this density.<ref name="PAMI95" /> This~~ is an iterative method, and we start with an initial estimate <math> x </math>. Let a [[Kernel (statistics)\|kernel function]] <math> K(x_i - x) </math> be given. This function determines the weight of nearby points for re-estimation of the mean. Typically Gaussian kernel on the distance to ~~the current estimate is used, <math> K(x_i - x) = e^{-c\|\|x_i - x\|\|^2} </math>~~. ~~The weighted mean of the density~~ in ~~the window determined by <math> K </math> is~~

	~~<math> m(x) = \frac{ \sum_{x_i \in N(x)} K(x_i - x) x_i } {\sum_{x_i \in N(x)} K(x_i - x)} </math>~~

	~~where <math> N(x) </math> is the neighborhood of <math> x </math>, a set of points for which <math> K(x) \neq 0 </math>~~.

	~~The mean-shift algorithm now sets <math> x \leftarrow m(x) </math>,~~ and ~~repeats the estimation until <math> m(x) </math> converges.~~

	~~== Mean shift for visual tracking ==~~
	~~The mean shift algorithm can~~ be used for visual tracking. The simplest such algorithm would create a confidence map in the new image based on the color histogram of the object in the previous image, and use mean shift to find the peak of a confidence map near the object's old position. The confidence map is a probability density function on the new image, assigning each pixel of the new image a probability, which is the probability of the pixel color occurring in the object in the previous image. ~~A few algorithms, such as [[ensemble tracking]],~~<~~ref name="avidan2001"~~>~~{{cite journal~~
	~~\| last = Avidan~~
	~~\| first = Shai~~
	~~\| authorlink =~~
	~~\| title = Ensemble Tracking~~
	~~\| journal = 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)~~
	~~\| volume = 2~~
	~~\| issue =~~
	~~\| pages =~~
	~~\| publisher = IEEE~~
	~~\| location = San Diego, California~~
	~~\| year = 2005~~
	~~\| url =~~
	~~\| doi =~~
	~~\| id =~~
	~~\| isbn = 0-7695-2372-2~~
	~~\| accessdate = }}~~<~~/ref~~> ~~CAMshift, expand on this idea.~~

	~~== See also ==~~
	*[[Kernel density estimation]] (KDE)
	*[[Kernel (statistics)]]

	~~== References ==~~
	~~{{reflist}}~~

	~~==Code implementations==~~
	* [http://scikit-~~learn~~.~~org/ Scikit-learn library] Numpy/Python implementation uses ball tree for efficient neighboring points lookup~~
	* [http://coewww.~~rutgers~~.~~edu/riul/research/code/EDISON/index.html EDISON library]. C++ implementation of mean-shift-based image segmentation. There is also a~~ [http://~~www.wisdom.weizmann.ac.il/~bagon/matlab.html#edison Matlab] interface for EDISON.~~
	* [http://sourceforge.net/projects/opencvlibrary/ OpenCV] contains mean-shift implementation via cvMeanShift Method
	* [http://code.google.com/~~p/aiphial/ Aiphial]~~. ~~Java-based mean-shift implementation for numeric data clustering and image segmentation~~
	* [http://mahout.apache.org Apache Mahout]. An map-reduce based implementation of MeanShift clustering written on Apache Hadoop.
	* [http://www.gergltd.com/~~cse486/project5/ CAMSHIFT project]. A MATLAB implementation of CAMSHIFT algorithm.~~
	* [http://www.orfeo-~~toolbox.org~~/~~doxygen-current~~/~~classotb_1_1MeanShiftImageFilter.html OTB MeanShift]. A C++ implementation using the [http://www.orfeo-toolbox.org Orfeo Toolbox].~~
	* [http://rsbweb.nih.gov/ij/plugins/mean-shift.html ImageJ Plug-in]. Image filtering using the mean shift filter.
	* [http://code.google.com/p/mean-shift/ Mean-shift google code]. An simple implementation of mean-shift as image filtering tool.

	~~==Short lessons==~~
	* [http://www.youtube.com/watch?v=M8B3RZVqgOo Here] a lesson is available from prof. M.Shah on this ~~topic;~~

	~~{{DEFAULTSORT:Mean~~-~~Shift}}~~
	~~[[Category:Computer vision]]~~
	~~[[Category:Data clustering algorithms]~~]

en>Quebec99: fixed reference

2014-01-31T18:28:02Z

fixed reference

← Older revision		Revision as of 20:28, 31 January 2014
Line 1:		Line 1:
	~~I would like to introduce myself to you~~, ~~I am Andrew~~ and ~~my wife doesn't like it at all~~. ~~To perform lacross~~ is the ~~thing I adore most~~ of ~~all~~. He is an ~~order clerk~~ and ~~it's some thing he really enjoy~~. ~~For years he's been living~~ in ~~Alaska~~ and ~~he doesn~~'~~t strategy~~ on ~~changing it~~.<br><br>~~Here is my site good psychic~~ ([http://~~c045~~.~~danah~~.co.kr/~~home~~/index.~~php?document_srl~~=~~1356970&mid~~=~~qna c045~~.~~danah~~.co.kr])		'''Mean shift''' is a [[non-parametric]] [[feature space\|feature-space]] analysis technique, a so-called [[mode seeking]] algorithm.<ref name="PAMI95">{{cite journal
			\| last = Cheng
			\| first = Yizong
			\| authorlink =
			\| title = Mean Shift, Mode Seeking, and Clustering
			\| journal = IEEE Transactions on Pattern Analysis and Machine Intelligence
			\| volume = 17
			\| issue = 8
			\| pages = 790–799
			\| publisher = IEEE
			\| location =
			\| date = August 1995
			\| url =
			\| doi = 10.1109/34.400568
			\| id =
			\| accessdate = }}</ref> Application domains include [[cluster analysis]] in [[computer vision]] and [[image processing]].<ref name="PAMI02">{{cite journal
			\| last = Comaniciu
			\| first = Dorin
			\| authorlink =
			\| coauthors = Peter Meer
			\| title = Mean Shift: A Robust Approach Toward Feature Space Analysis
			\| journal = IEEE Transactions on Pattern Analysis and Machine Intelligence
			\| volume = 24
			\| issue = 5
			\| pages = 603–619
			\| publisher = IEEE
			\| location =
			\| date = May 2002
			\| url =
			\| doi = 10.1109/34.1000236
			\| id =
			\| accessdate = 2008-02-29}}</ref>

			== History ==
			The mean shift procedure was originally presented in 1975 by Fukunaga and Hostetler.<ref name="Fukunaga">{{cite journal
			\| last = Fukunaga
			\| first = Keinosuke
			\| authorlink =
			\| coauthors = Larry D. Hostetler
			\| title = The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition
			\| journal = IEEE Transactions on Information Theory
			\| volume = 21
			\| issue = 1
			\| pages = 32–40
			\| publisher = IEEE
			\| location =
			\| date = January 1975
			\| url = http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1055330
			\| doi =10.1109/TIT.1975.1055330
			\| id =
			\| accessdate = 2008-02-29}}</ref>

			== Overview ==
			Mean shift is a procedure for locating the maxima of a [[density function]] given discrete data sampled from that function.<ref name="PAMI95" /> It is useful for detecting the [[Mode (statistics)\|mode]]s of this density.<ref name="PAMI95" /> This is an iterative method, and we start with an initial estimate <math> x </math>. Let a [[Kernel (statistics)\|kernel function]] <math> K(x_i - x) </math> be given. This function determines the weight of nearby points for re-estimation of the mean. Typically Gaussian kernel on the distance to the current estimate is used, <math> K(x_i - x) = e^{-c\|\|x_i - x\|\|^2} </math>. The weighted mean of the density in the window determined by <math> K </math> is

			<math> m(x) = \frac{ \sum_{x_i \in N(x)} K(x_i - x) x_i } {\sum_{x_i \in N(x)} K(x_i - x)} </math>

			where <math> N(x) </math> is the neighborhood of <math> x </math>, a set of points for which <math> K(x) \neq 0 </math>.

			The mean-shift algorithm now sets <math> x \leftarrow m(x) </math>, and repeats the estimation until <math> m(x) </math> converges.

			== Mean shift for visual tracking ==
			The mean shift algorithm can be used for visual tracking. The simplest such algorithm would create a confidence map in the new image based on the color histogram of the object in the previous image, and use mean shift to find the peak of a confidence map near the object's old position. The confidence map is a probability density function on the new image, assigning each pixel of the new image a probability, which is the probability of the pixel color occurring in the object in the previous image. A few algorithms, such as [[ensemble tracking]],<ref name="avidan2001">{{cite journal
			\| last = Avidan
			\| first = Shai
			\| authorlink =
			\| title = Ensemble Tracking
			\| journal = 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
			\| volume = 2
			\| issue =
			\| pages =
			\| publisher = IEEE
			\| location = San Diego, California
			\| year = 2005
			\| url =
			\| doi =
			\| id =
			\| isbn = 0-7695-2372-2
			\| accessdate = }}</ref> CAMshift, expand on this idea.

			== See also ==
			*[[Kernel density estimation]] (KDE)
			*[[Kernel (statistics)]]

			== References ==
			{{reflist}}

			==Code implementations==
			* [http://scikit-learn.org/ Scikit-learn library] Numpy/Python implementation uses ball tree for efficient neighboring points lookup
			* [http://coewww.rutgers.edu/riul/research/code/EDISON/index.html EDISON library]. C++ implementation of mean-shift-based image segmentation. There is also a [http://www.wisdom.weizmann.ac.il/~bagon/matlab.html#edison Matlab] interface for EDISON.
			* [http://sourceforge.net/projects/opencvlibrary/ OpenCV] contains mean-shift implementation via cvMeanShift Method
			* [http://code.google.com/p/aiphial/ Aiphial]. Java-based mean-shift implementation for numeric data clustering and image segmentation
			* [http://mahout.apache.org Apache Mahout]. An map-reduce based implementation of MeanShift clustering written on Apache Hadoop.
			* [http://www.gergltd.com/cse486/project5/ CAMSHIFT project]. A MATLAB implementation of CAMSHIFT algorithm.
			* [http://www.orfeo-toolbox.org/doxygen-current/classotb_1_1MeanShiftImageFilter.html OTB MeanShift]. A C++ implementation using the [http://www.orfeo-toolbox.org Orfeo Toolbox].
			* [http://rsbweb.nih.gov/ij/plugins/mean-shift.html ImageJ Plug-in]. Image filtering using the mean shift filter.
			* [http://code.google.com/p/mean-shift/ Mean-shift google code]. An simple implementation of mean-shift as image filtering tool.

			==Short lessons==
			* [http://www.youtube.com/watch?v=M8B3RZVqgOo Here] a lesson is available from prof. M.Shah on this topic;

			{{DEFAULTSORT:Mean-Shift}}
			[[Category:Computer vision]]
			[[Category:Data clustering algorithms]]

en>Kilom691: ref corrected

2012-02-11T09:19:43Z

ref corrected

New page

I would like to introduce myself to you, I am Andrew and my wife doesn't like it at all. To perform lacross is the thing I adore most of all. He is an order clerk and it's some thing he really enjoy. For years he's been living in Alaska and he doesn't strategy on changing it.<br><br>Here is my site good psychic ([http://c045.danah.co.kr/home/index.php?document_srl=1356970&mid=qna c045.danah.co.kr])

← Older revision		Revision as of 21:58, 3 January 2015
Line 1:		Line 1:
	~~'''Mean shift'''~~ is ~~a [[non-parametric]] [[feature space\|feature-space]] analysis technique, a so-called [[mode seeking]] algorithm.<ref name="PAMI95">{{cite journal~~		Andrew Simcox is the title his parents gave him and he totally enjoys this name. Playing badminton is a thing that he is totally addicted to. Her family lives in Alaska but her spouse wants them to transfer. I am an invoicing officer and I'll be promoted quickly.<br><br>My web-site ... free psychic reading ([http://breenq.com/index.php?do=/profile-1144/info/ go to this web-site])
	~~\| last = Cheng~~
	~~\| first = Yizong~~
	~~\| authorlink =~~
	\| title ~~= Mean Shift, Mode Seeking,~~ and ~~Clustering~~
	~~\| journal = IEEE Transactions on Pattern Analysis and Machine Intelligence~~
	~~\| volume = 17~~
	~~\| issue = 8~~
	~~\| pages = 790–799~~
	~~\| publisher = IEEE~~
	~~\| location =~~
	~~\| date = August 1995~~
	~~\| url =~~
	~~\| doi = 10.1109/34.400568~~
	~~\| id =~~
	~~\| accessdate = }}</ref> Application domains include [[cluster analysis]] in [[computer vision]] and [[image processing]].<ref name="PAMI02">{{cite journal~~
	~~\| last = Comaniciu~~
	~~\| first = Dorin~~
	~~\| authorlink =~~
	~~\| coauthors = Peter Meer~~
	~~\| title = Mean Shift: A Robust Approach Toward Feature Space Analysis~~
	~~\| journal = IEEE Transactions on Pattern Analysis and Machine Intelligence~~
	~~\| volume = 24~~
	~~\| issue = 5~~
	~~\| pages = 603–619~~
	~~\| publisher = IEEE~~
	~~\| location =~~
	~~\| date = May 2002~~
	~~\| url =~~
	~~\| doi = 10.1109/34.1000236~~
	~~\| id =~~
	~~\| accessdate = 2008-02-29}}</ref>~~

	~~== History ==~~
	~~The mean shift procedure was originally presented in 1975 by Fukunaga and Hostetler.<ref~~ name~~="Fukunaga">{{cite journal~~
	~~\| last = Fukunaga~~
	~~\| first = Keinosuke~~
	~~\| authorlink =~~
	~~\| coauthors = Larry D~~. ~~Hostetler~~
	~~\| title = The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition~~
	~~\| journal = IEEE Transactions on Information Theory~~
	~~\| volume = 21~~
	~~\| issue = 1~~
	~~\| pages = 32–40~~
	~~\| publisher = IEEE~~
	~~\| location =~~
	~~\| date = January 1975~~
	~~\| url = http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1055330~~
	~~\| doi =10.1109/TIT.1975.1055330~~
	~~\| id =~~
	~~\| accessdate = 2008-02-29}}</ref>~~

	~~== Overview ==~~
	~~Mean shift~~ is a ~~procedure for locating the maxima of a [[density function]] given discrete data sampled from~~ that ~~function.<ref name="PAMI95" /> It is useful for detecting the [[Mode (statistics)\|mode]]s of this density.<ref name="PAMI95" /> This~~ is an iterative method, and we start with an initial estimate <math> x </math>. Let a [[Kernel (statistics)\|kernel function]] <math> K(x_i - x) </math> be given. This function determines the weight of nearby points for re-estimation of the mean. Typically Gaussian kernel on the distance to ~~the current estimate is used, <math> K(x_i - x) = e^{-c\|\|x_i - x\|\|^2} </math>~~. ~~The weighted mean of the density~~ in ~~the window determined by <math> K </math> is~~

	~~<math> m(x) = \frac{ \sum_{x_i \in N(x)} K(x_i - x) x_i } {\sum_{x_i \in N(x)} K(x_i - x)} </math>~~

	~~where <math> N(x) </math> is the neighborhood of <math> x </math>, a set of points for which <math> K(x) \neq 0 </math>~~.

	~~The mean-shift algorithm now sets <math> x \leftarrow m(x) </math>,~~ and ~~repeats the estimation until <math> m(x) </math> converges.~~

	~~== Mean shift for visual tracking ==~~
	~~The mean shift algorithm can~~ be used for visual tracking. The simplest such algorithm would create a confidence map in the new image based on the color histogram of the object in the previous image, and use mean shift to find the peak of a confidence map near the object's old position. The confidence map is a probability density function on the new image, assigning each pixel of the new image a probability, which is the probability of the pixel color occurring in the object in the previous image. ~~A few algorithms, such as [[ensemble tracking]],~~<~~ref name="avidan2001"~~>~~{{cite journal~~
	~~\| last = Avidan~~
	~~\| first = Shai~~
	~~\| authorlink =~~
	~~\| title = Ensemble Tracking~~
	~~\| journal = 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)~~
	~~\| volume = 2~~
	~~\| issue =~~
	~~\| pages =~~
	~~\| publisher = IEEE~~
	~~\| location = San Diego, California~~
	~~\| year = 2005~~
	~~\| url =~~
	~~\| doi =~~
	~~\| id =~~
	~~\| isbn = 0-7695-2372-2~~
	~~\| accessdate = }}~~<~~/ref~~> ~~CAMshift, expand on this idea.~~

	~~== See also ==~~
	*[[Kernel density estimation]] (KDE)
	*[[Kernel (statistics)]]

	~~== References ==~~
	~~{{reflist}}~~

	~~==Code implementations==~~
	* [http://scikit-~~learn~~.~~org/ Scikit-learn library] Numpy/Python implementation uses ball tree for efficient neighboring points lookup~~
	* [http://coewww.~~rutgers~~.~~edu/riul/research/code/EDISON/index.html EDISON library]. C++ implementation of mean-shift-based image segmentation. There is also a~~ [http://~~www.wisdom.weizmann.ac.il/~bagon/matlab.html#edison Matlab] interface for EDISON.~~
	* [http://sourceforge.net/projects/opencvlibrary/ OpenCV] contains mean-shift implementation via cvMeanShift Method
	* [http://code.google.com/~~p/aiphial/ Aiphial]~~. ~~Java-based mean-shift implementation for numeric data clustering and image segmentation~~
	* [http://mahout.apache.org Apache Mahout]. An map-reduce based implementation of MeanShift clustering written on Apache Hadoop.
	* [http://www.gergltd.com/~~cse486/project5/ CAMSHIFT project]. A MATLAB implementation of CAMSHIFT algorithm.~~
	* [http://www.orfeo-~~toolbox.org~~/~~doxygen-current~~/~~classotb_1_1MeanShiftImageFilter.html OTB MeanShift]. A C++ implementation using the [http://www.orfeo-toolbox.org Orfeo Toolbox].~~
	* [http://rsbweb.nih.gov/ij/plugins/mean-shift.html ImageJ Plug-in]. Image filtering using the mean shift filter.
	* [http://code.google.com/p/mean-shift/ Mean-shift google code]. An simple implementation of mean-shift as image filtering tool.

	~~==Short lessons==~~
	* [http://www.youtube.com/watch?v=M8B3RZVqgOo Here] a lesson is available from prof. M.Shah on this ~~topic;~~

	~~{{DEFAULTSORT:Mean~~-~~Shift}}~~
	~~[[Category:Computer vision]]~~
	~~[[Category:Data clustering algorithms]~~]