added more results to tutorial page

opencv · Oct 30, 2020 · 0623e72 · 0623e72
1 parent 95c7f12
commit 0623e72
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 4 deletions.
diff --git a/modules/alphamat/tutorials/alphamat_tutorial.markdown b/modules/alphamat/tutorials/alphamat_tutorial.markdown
@@ -15,10 +15,17 @@ Input Image: ![](../samples/input_images/plant.jpg)
 Input image should be preferably a RGB image.
 Input Trimap: ![](../samples/trimaps/plant.png)
 The trimap image is a greyscale image that contains information about the foreground(white pixels), background(black pixels) and unknown(grey) pixels.
-Output alpha Matte: ![](../samples/output_mattes/plant_result.jpg)
-The computed alpha matte is saved as a greyscale image with values that indicate the opacity of the extracted foreground object. These opacity values can be used to blend the foreground objects into a new backgound.
+Output alpha Matte: ![](../samples/output_mattes/plant_result.png)
+The computed alpha matte is saved as a greyscale image where the pixel values indicate the opacity of the extracted foreground object. These opacity values can be used to blend the foreground object into a diffferent backgound, as shown below:
+![](./images/plant_new_backgrounds.jpg)
+
+Following are some more results. 
+![](./images/matting_results.jpg)
+
+The first column is input RGB image, the second column is input trimap, third column is the extracted alphamatte and the last two columns show the foreground object blended on new backgrounds.
+
+This project is implementation of @cite aksoy2017designing . It also required implementation of parts of other papers [2,3,4]. 
 
-This project is implementation of @cite aksoy2017designing . It also required implementation of parts of other papers [2,3,4].
 
 # Building
 
@@ -42,7 +49,6 @@ The built target can be tested as follows:
 
 @includelineno alphamat/samples/information_flow_matting.cpp
 
-
 # References
 
 [1] Yagiz Aksoy, Tunc Ozan Aydin, Marc Pollefeys, [Designing Effective Inter-Pixel Information Flow for Natural Image Matting](https://www.researchgate.net/publication/318489370_Designing_Effective_Inter-Pixel_Information_Flow_for_Natural_Image_Matting), CVPR, 2017.

diff --git a/modules/alphamat/tutorials/matting_results.jpg b/modules/alphamat/tutorials/matting_results.jpg
diff --git a/modules/alphamat/tutorials/plant_new_backgrounds.jpg b/modules/alphamat/tutorials/plant_new_backgrounds.jpg