net.semanticmetadata.lire.imageanalysis.visualattention

类 StentifordModel

java.lang.Object

net.semanticmetadata.lire.imageanalysis.visualattention.StentifordModel

public class StentifordModel
extends java.lang.Object

Implements a visual attention model described in F. W. M. Stentiford, An estimator for visual attention through competitive novelty with application to image compression, Proc. Picture Coding Symposium, pp 101-104, Seoul, 24-27 April, 2001.

作者:

Mathias Lux, mathias@juggle.at, http://www.semanticmetadata.net Date: 22.03.2010 Time: 15:52:24

构造器概要

构造器

构造器和说明
StentifordModel() Default constructor with default values.
StentifordModel(int neighbourhoodSize, int maxChecks, int maxDist) Constructor for advance use.

方法概要

限定符和类型	方法和说明
void	extract(java.awt.image.BufferedImage img)
int[][]	getAttentionModel()
java.awt.image.BufferedImage	getAttentionVisualization() Visualizes the attention model in a picture.

从类继承的方法 java.lang.Object

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

构造器详细资料

StentifordModel

public StentifordModel(int neighbourhoodSize,
                       int maxChecks,
                       int maxDist)

Constructor for advance use. Instead of using the default values they can be set.

参数:

neighbourhoodSize - number of pixels selected from the neighbourhood

maxChecks - number of random checks for each pixels, according to the paper 100 should work fine.

maxDist - the maximum distance between colors to be deemed similar

StentifordModel

public StentifordModel()

Default constructor with default values.

方法详细资料

extract

public void extract(java.awt.image.BufferedImage img)

getAttentionModel

public int[][] getAttentionModel()

getAttentionVisualization

public java.awt.image.BufferedImage getAttentionVisualization()

Visualizes the attention model in a picture. Lighter pixels are the ones with more attention.

返回:

an image visualizing the attention model