Classify pixels using hyper-cuboids.

class_ndim_box classifies the pixels of the multi-channel image given in MultiChannelImage. To do so, the classificator ClassifHandle created with create_class_box is used. The classificator can be trained using learn_ndim_box or as described with create_class_box. More information on the structure of the classificator can be found also under that operator.

MultiChannelImage is a multi channel image. Its pixel values are used for the classification.

read_image(Bild,'meer') 
disp_image(Image,WindowHandle) 
set_color(WindowHandle,'green') 
fwrite_string('Draw the learning region') 
fnew_line() 
draw_region(Reg1,WindowHandle) 
reduce_domain(Image,Reg1,Foreground) 
set_color(WindowHandle,'red') 
fwrite_string('Draw Background') 
fnew_line() 
draw_region(Reg2,WindowHandle) 
reduce_domain(Image,Reg2,Background) 
fwrite_string('Start to learn') 
fnew_line() 
create_classif(ClassifHandle) 
class_ndim_box(Foreground,Background,Image,ClassifHandle) 
fwrite_string('start to classificate') 
fnew_line() 
class_ndim_box(Image,Res,ClassifHandle) 
set_draw(WindowHandle,'fill') 
disp_region(Res,WindowHandle) 
free_classif(ClassifHandle).

Let N be the number of hyper-cuboids and F be the area of the input region. Then the runtime complexity is O(N * F).

class_ndim_box returns 2 (H_MSG_TRUE) if all parameters are correct. The behavior with respect to the input images and output regions can be determined by setting the values of the flags 'no_object_result', 'empty_region_result', and 'store_empty_region' with set_system. If necessary, an exception is raised.

class_ndim_box is local and processed completely exclusively without parallelization.

create_class_box, learn_class_box, median_image, compose2, compose3, compose4

class_ndim_norm, class_2dim_sup

class_ndim_box, descript_class_box, create_class_box

Region processing