org.openimaj.image.feature.local.detector.mser

Class MSERDetector

java.lang.Object

org.openimaj.image.feature.local.detector.mser.MSERDetector

@Reference(type=Article,
           author={"J Matas","O Chum","M Urban","T Pajdla"},
           title="Robust wide-baseline stereo from maximally stable extremal regions",
           year="2004",
           journal="Image and Vision Computing",
           pages={"761 "," 767"},
           url="http://www.sciencedirect.com/science/article/pii/S0262885604000435",
           number="10",
           volume="22",
           customData={"issn","0262-8856","doi","10.1016/j.imavis.2004.02.006","keywords","Robust metric"})
public class MSERDetector
extends Object

Takes a merge tree from the watershed algorithm and detects MSERs. The detect() method returns a list of MSER components. The components are also marked as MSERs in the merge tree, such that the tree can be used to determine the hierarchical nature of the MSERs. Use the Component.isMSER to determine if the component in the tree is an MSER.

(From http://www.vlfeat.org/overview/mser.html) The stability of an extremal region R is the inverse of the relative area variation of the region R when the intensity level is increased by d. Formally, the variation is defined as:

 
 |R(+d) - R|
 -----------
      |R|
  
 

where |R| denotes the area of the extremal region R, R(+d) is the extremal region +d levels up which contains R and |R(+d) - R| is the area difference of the two regions. A stable region has a small variation. The algorithm finds regions which are "maximally stable", meaning that they have a lower variation than the regions one level below or above. Note that due to the discrete nature of the image, the region below / above may be coincident with the actual region, in which case the region is still deemed maximal. However, even if an extremal region is maximally stable, it might be rejected if: it is too big (see the parameter maxArea); it is too small (see the parameter minArea); it is too unstable (see the parameter maxVariation); it is too similar to its parent MSER (see the parameter minDiversity).

Author:

David Dupplaw (dpd@ecs.soton.ac.uk)

Constructor Summary

Constructors

Constructor and Description
MSERDetector(TreeNode<Component> mergeTree) Constructor that takes the merge tree from the watershed algorithm.

Method Summary

Modifier and Type	Method and Description
List<Component>	detect() Detect MSERs in the merge tree provided in the constructor.
int	getDelta()
int	getMaxArea()
float	getMaxVariation()
TreeNode<Component>	getMergeTree()
int	getMinArea()
float	getMinDiversity()
void	setDelta(int delta)
void	setMaxArea(int maxArea)
void	setMaxVariation(float maxVariation)
void	setMinArea(int minArea)
void	setMinDiversity(float minDiversity)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

MSERDetector

public MSERDetector(TreeNode<Component> mergeTree)

Constructor that takes the merge tree from the watershed algorithm.

Parameters:

mergeTree - The merge tree

Method Detail

detect

public List<Component> detect()

Detect MSERs in the merge tree provided in the constructor.

Returns:

a list of detected regions.

getMaxArea

public int getMaxArea()

Returns:

the maxArea

setMaxArea

public void setMaxArea(int maxArea)

Parameters:

maxArea - the maxArea to set

getMinArea

public int getMinArea()

Returns:

the minArea

setMinArea

public void setMinArea(int minArea)

Parameters:

minArea - the minArea to set

getMaxVariation

public float getMaxVariation()

Returns:

the maxVariation

setMaxVariation

public void setMaxVariation(float maxVariation)

Parameters:

maxVariation - the maxVariation to set

getMinDiversity

public float getMinDiversity()

Returns:

the minDiversity

setMinDiversity

public void setMinDiversity(float minDiversity)

Parameters:

minDiversity - the minDiversity to set

getMergeTree

public TreeNode<Component> getMergeTree()

Returns:

the mergeTree

getDelta

public int getDelta()

Returns:

the delta

setDelta

public void setDelta(int delta)

Parameters:

delta - the delta to set