Merge pull request #4 from sunitanyk/test_alphamatte_sn

Test alphamatte sn

Author: muskaankularia

modules/README.md

@@ -10,6 +10,8 @@ $ cmake -D OPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules -D BUILD_opencv_<r
 
 - **aruco**: ArUco and ChArUco Markers -- Augmented reality ArUco marker and "ChARUco" markers where ArUco markers embedded inside the white areas of the checker board.
 
+- **alphamat**: Computer Vision based Alpha Matting -- Given an input image and a trimap, generate an alpha matte.
+
 - **bgsegm**: Background segmentation algorithm combining statistical background image estimation and per-pixel Bayesian segmentation.
 
 - **bioinspired**: Biological Vision -- Biologically inspired vision model: minimize noise and luminance variance, transient event segmentation, high dynamic range tone mapping methods.

modules/alphamat/README.md

@@ -19,11 +19,13 @@ E represents the deviation of unknown pixels opacity or colour from what we pred
 
 Pre-processing and post-processing is implemented in **trimming.hpp**
 
-To run the code -
-1. **g++ -std=c++11 alphac.cpp \`pkg-config --cflags --libs opencv\`**
-1. **./a.out \<path to image> \<path to corresponding trimap>**
+Compile the module using -
+```
+cmake -DOPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules -Dopencv_alphamat=ON <opencv_source_dir>
+make
+```
 
-Sample image and trimap are in opencv_contrib/modules/alphamat/src/img and opencv_contrib/modules/alphamat/src/trimap
+Sample image and trimap are in opencv_contrib/modules/alphamat/src/input_images and opencv_contrib/modules/alphamat/src/trimaps
 
 ## Results
 

modules/alphamat/samples/alphamat_information_flow.cpp renamed to modules/alphamat/samples/information_flow_matting.cpp

@@ -0,0 +1,19 @@
+Information Flow AlphaMatting {#tutorial_alphamat_information_flow}
+=============================
+
+Alphamatting is the problem of extracting the foreground from an image. Given the input of image and its corresponding trimap, we try to extract the foreground from the background. Following is an example -
+
+Input Image: ![](images/net_input_image.jpg)
+Input Trimap: ![](images/net_trimap.jpg)
+Output alpha Matte: ![](images/net_result.jpg)
+
+Build the module using -
+```
+cmake -DOPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules -Dopencv_alphamat=ON <opencv_source_dir>
+make
+```
+
+Usage Example
+-------------
+
+@includelineno alphamat/samples/information_flow_matting.cpp

modules/alphamat/samples/img/elephant.png renamed to modules/alphamat/samples/input_images/elephant.png

@@ -1,6 +1,14 @@
-Tutorials for alphamat module {#tutorial_table_of_content_alphamat}
-===============================================================
+Information Flow Alpha Matting {#tutorial_table_of_content_alphamat}
+==============================
 
--   @subpage tutorial_alphamat_information_flow
+-   @subpage tutorial_information_flow_matting
 
-    In several applications, we need to extract foreground for further operations like changing the background in an image. Information-Flow Matting is a computer vision approach to compute alphamatte of objects in images.
+    *Author:* Muskaan Kularia
+
+    *Mentor:* Sunita Nayak
+
+    This project was part of Google Summer of Code 2019.
+
+    In several applications, we need to extract foreground for further operations like changing the background in an image. Information-Flow Matting is a computer vision approach to compute alphamatte of objects in images. This work is based on the following paper:
+
+    Yagiz Aksoy, Tunc Ozan Aydin, Marc Pollefeys, [Designing Effective Inter-Pixel Information Flow for Natural Image Matting](http://people.inf.ethz.ch/aksoyy/papers/CVPR17-ifm.pdf), CVPR, 2017.