cooc_feature

Herror ::cooc_feature_image ( Hobject Regions, Hobject Image, const HTuple &LdGray, const HTuple &Direction, double *Energy, double *Correlation, double *Homogenity, double *Contrast ) Herror ::cooc_feature_image ( Hobject Regions, Hobject Image, const HTuple &LdGray, const HTuple &Direction, HTuple *Energy, HTuple *Correlation, HTuple *Homogenity, HTuple *Contrast ) double HRegion::CoocFeatureImage ( const HImage &Image, const HTuple &LdGray, const HTuple &Direction, double *Correlation, double *Homogenity, double *Contrast ) const HTuple HRegionArray::CoocFeatureImage ( const HImage &Image, const HTuple &LdGray, const HTuple &Direction, HTuple *Correlation, HTuple *Homogenity, HTuple *Contrast ) const

Calculate a co-occurrence matrix and derive gray value features thereof.

The call of ::cooc_feature_image corresponds to the consecutive execution of the operators ::gen_cooc_matrix and ::cooc_feature_matrix. If several direction matrices of the co-occurrence matrix are to be evaluated consecutively, it is more efficient to generate the matrix via ::gen_cooc_matrix and then call the operator ::cooc_feature_matrix for the resulting matrix. The parameter Direction transfers the direction of the neighborhood in angle or 'mean'. In the case of 'mean' the mean value is calculated in all four directions.

Parameters

`Regions` (input_object)	region(-array) `->` Hobject: HRegion(Array)
Region to be examined.

`Image` (input_object)	image `->` Hobject: HImage ( byte )
Corresponding gray values.

`LdGray` (input_control)	integer `->` HTuple.long
Number of gray values to be distinguished (2^LdGray).
Default value: 6
List of values: 1, 2, 3, 4, 5, 6, 7, 8

`Direction` (input_control)	integer `->` HTuple.long / char *
Direction in which the matrix is to be calculated.
Default value: 0
List of values: 0, 45, 90, 135, 'mean'

`Energy` (output_control)	real(-array) `->` (HTuple.) double *
Gray value energy.

`Correlation` (output_control)	real(-array) `->` (HTuple.) double *
Correlation of gray values.

`Homogenity` (output_control)	real(-array) `->` (HTuple.) double *
Local homogenity of gray values.

`Contrast` (output_control)	real(-array) `->` (HTuple.) double *
Gray value contrast.

Result

The operator ::cooc_feature_image returns the value H_MSG_TRUE if an image with defined gray values (byte) is entered and the parameters are correct. The behavior in case of empty input (no input images available) is set via the operator ::set_system('no_object_result',<Result>), the behavior in case of empty region is set via ::set_system('empty_region_result',<Result>). If necessary an exception handling is raised.

Possible Predecessors

::gen_cooc_matrix

Alternatives

::cooc_feature_matrix

Module

Image filters