Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revision Both sides next revision
interimage:attributes_description [2010/06/23 17:57]
rsilva
interimage:attributes_description [2012/07/12 18:27]
rsilva
Line 30: Line 30:
   * **yGeoCenter** - y geo-coordinate of the object centroid.   * **yGeoCenter** - y geo-coordinate of the object centroid.
   * **membership** or **p** - confidence in the object with regard to its classification.   * **membership** or **p** - confidence in the object with regard to its classification.
 +
  
  
 ===== Shape Attributes ===== ===== Shape Attributes =====
  
-  * **area** - Returns the area of the given polygon, in number of pixels.+  * **area** - Returns the real area of the given polygon.
   * **bBoxArea** - Returns the bounding box area of the given polygon, in number of pixels.   * **bBoxArea** - Returns the bounding box area of the given polygon, in number of pixels.
   * **perimeter** - Returns the perimeter of the polygon, considering the amount of pixels in its border.   * **perimeter** - Returns the perimeter of the polygon, considering the amount of pixels in its border.
Line 58: Line 59:
  {{ :​interimage:​shapeindex.png }}  {{ :​interimage:​shapeindex.png }}
 Where P is the polygon perimeter and A is the area. Where P is the polygon perimeter and A is the area.
 +
 +
 +
 +
 +
  
 ===== Spectral Statistical Attributes ===== ===== Spectral Statistical Attributes =====
  
-  * **Amplitude** - represents the difference between the maximum and minimum pixel values of a region ​for the given image band/​channel.+  * **Amplitude** - represents the difference between the maximum and minimum pixel values of an object ​for the given image layer **L**.
  
-  * **Brightness** -  +  * **Brightness** - represents the brightness of an image object.
  
   * **Correlation** - Correlation is a similarity measure between two data sets under an absolute scale between [-1,1]. It is calculated as shown by the next formula:   * **Correlation** - Correlation is a similarity measure between two data sets under an absolute scale between [-1,1]. It is calculated as shown by the next formula:
Line 87: Line 93:
  
  
-  * **Ratio** -+  * **Ratio** - represents the amount that layer **L** contributes to the total brightness of an image object.
  
   * **StdDeviation** - The standard deviation represents the numerical data dispersion degree surrounding the mean. It is defined by:   * **StdDeviation** - The standard deviation represents the numerical data dispersion degree surrounding the mean. It is defined by:
Line 94: Line 100:
   * **SumPixelsValues** - Represents the sum of all element values inside an area for one given image band/​channel.   * **SumPixelsValues** - Represents the sum of all element values inside an area for one given image band/​channel.
  
-a  ​* **Variance** - Like the standard deviation, the variance also represents the numerical data dispersion degree surrounding the mean but in the original data value scale. It is defined by:+  ​* **Variance** - Like the standard deviation, the variance also represents the numerical data dispersion degree surrounding the mean but in the original data value scale. It is defined by:
 {{ interimage:​att_variance.gif }} {{ interimage:​att_variance.gif }}
  

Navigation