SPLREG

Description

SPLREG calculates the coefficients of a first-order linear regression equation which relates gray-level values in two image layers.

Parameters

Name	Type	Length	Value range
Input 1: Input 1 *	Raster port	1 -
Input 2: Input layer 2 *	Raster port	1 -
Resample Mode: Resample mode	Raster port	5 - 1	Nearest | Bilinear | Cubic Default: Nearest
Mask: Area mask	Bitmap port	0 - 4
Regression equation intercept	Float	0 - 1
Regression equation slope	Float	0 - 1
Coefficient of Non-Determination (1-R^2)	Float	0 - 1
Correlation Coefficient (R)	Float	0 - 1
Number of samples	Float	0 - 1
Report	String	0 - 192	See parameter description

* Required parameter

Parameter descriptions

Input 1: Input 1

Specifies input image layer 1 for which the linear regression equation is calculated.

Input 2: Input layer 2

Specifies input image layer 2 for which the linear regression equation is calculated.

Resample Mode: Resample mode

The default value is Nearest.

Mask: Area mask

Specifies the window or bitmap that defines the area to be processed within the input raster.

If no value is specified, the entire channel is processed.

Regression equation intercept

Generated by SPLREG. Specifies the value of coefficient A of the first-order linear regression equation that relates gray-level values in two specified image layers (Input1 and Input2).

Regression equation slope

Generated by SPLREG. Specifies the value of coefficient B of the first-order linear regression equation that relates gray-level values in two specified image layers (Input1 and Input2).

Coefficient of Non-Determination (1-R^2)

Generated by SPLREG. Specifies the Coefficient of Non-Determination (1 - R^2) value, from the first-order linear regression equation that relates gray-level values in two specified image layers (Input1 and Input2).

Correlation Coefficient (R)

Generated by SPLREG. Specifies the Correlation Coefficient (R) value, from the first-order linear regression equation that relates gray-level values in two specified image layers (Input1 and Input2).

Number of samples

Generated by SPLREG. Specifies is the number of samples used for the regression.

Report

Specifies where to direct the generated report.

Available options are:

• LOG: generates a report on the terminal (default)
• <modulename.RPT>: appends a report to the module's RPT file
• DISK: generates a report on file "IMPRPT.LST"

Details

SPLREG determines the coefficients for a first-order linear regression equation that relates gray-level values in two specified image channels, and saves the coefficient values, the Coefficient of Non-Determination (1 - R^2) and Correlation Coefficient (R) and the number of samples in the output parameters (A, B, 1 - R^2, R, number of samples). The equation specifies a straight line which would go through a scatterplot. The Coefficient of Non-Determination (1 - R^2) indicates the amount of variation in X that is not explained by the regression equation. If X and Y are perfectly correlated, 1 - R^2 = 0; if X and Y are totally uncorrelated, 1 - R^2 = 1.

The MASK parameter specifies the area within the input channel to be sampled for calculation of the linear regression equation. Only the area under the MASK is processed; the rest of the image is not used in the calculations.