OpenCV  3.0.0
Open Source Computer Vision
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Properties Friends Macros Groups Pages
Interactive Foreground Extraction using GrabCut Algorithm

Goal

In this chapter

Theory

GrabCut algorithm was designed by Carsten Rother, Vladimir Kolmogorov & Andrew Blake from Microsoft Research Cambridge, UK. in their paper, "GrabCut": interactive foreground extraction using iterated graph cuts . An algorithm was needed for foreground extraction with minimal user interaction, and the result was GrabCut.

How it works from user point of view ? Initially user draws a rectangle around the foreground region (foreground region shoule be completely inside the rectangle). Then algorithm segments it iteratively to get the best result. Done. But in some cases, the segmentation won't be fine, like, it may have marked some foreground region as background and vice versa. In that case, user need to do fine touch-ups. Just give some strokes on the images where some faulty results are there. Strokes basically says *"Hey, this region should be foreground, you marked it background, correct it in next iteration"* or its opposite for background. Then in the next iteration, you get better results.

See the image below. First player and football is enclosed in a blue rectangle. Then some final touchups with white strokes (denoting foreground) and black strokes (denoting background) is made. And we get a nice result.

grabcut_output1.jpg
image

So what happens in background ?

It is illustrated in below image (Image Courtesy: http://www.cs.ru.ac.za/research/g02m1682/)

grabcut_scheme.jpg
image

Demo

Now we go for grabcut algorithm with OpenCV. OpenCV has the function, cv2.grabCut() for this. We will see its arguments first:

First let's see with rectangular mode. We load the image, create a similar mask image. We create fgdModel and bgdModel. We give the rectangle parameters. It's all straight-forward. Let the algorithm run for 5 iterations. Mode should be cv2.GC_INIT_WITH_RECT since we are using rectangle. Then run the grabcut. It modifies the mask image. In the new mask image, pixels will be marked with four flags denoting background/foreground as specified above. So we modify the mask such that all 0-pixels and 2-pixels are put to 0 (ie background) and all 1-pixels and 3-pixels are put to 1(ie foreground pixels). Now our final mask is ready. Just multiply it with input image to get the segmented image.

1 import numpy as np
2 import cv2
3 from matplotlib import pyplot as plt
4 
5 img = cv2.imread('messi5.jpg')
6 mask = np.zeros(img.shape[:2],np.uint8)
7 
8 bgdModel = np.zeros((1,65),np.float64)
9 fgdModel = np.zeros((1,65),np.float64)
10 
11 rect = (50,50,450,290)
12 cv2.grabCut(img,mask,rect,bgdModel,fgdModel,5,cv2.GC_INIT_WITH_RECT)
13 
14 mask2 = np.where((mask==2)|(mask==0),0,1).astype('uint8')
15 img = img*mask2[:,:,np.newaxis]
16 
17 plt.imshow(img),plt.colorbar(),plt.show()

See the results below:

grabcut_rect.jpg
image

Oops, Messi's hair is gone. Who likes Messi without his hair? We need to bring it back. So we will give there a fine touchup with 1-pixel (sure foreground). At the same time, Some part of ground has come to picture which we don't want, and also some logo. We need to remove them. There we give some 0-pixel touchup (sure background). So we modify our resulting mask in previous case as we told now.

What I actually did is that, I opened input image in paint application and added another layer to the image. Using brush tool in the paint, I marked missed foreground (hair, shoes, ball etc) with white and unwanted background (like logo, ground etc) with black on this new layer. Then filled remaining background with gray. Then loaded that mask image in OpenCV, edited original mask image we got with corresponding values in newly added mask image. Check the code below:

1 # newmask is the mask image I manually labelled
2 newmask = cv2.imread('newmask.png',0)
3 
4 # whereever it is marked white (sure foreground), change mask=1
5 # whereever it is marked black (sure background), change mask=0
6 mask[newmask == 0] = 0
7 mask[newmask == 255] = 1
8 
9 mask, bgdModel, fgdModel = cv2.grabCut(img,mask,None,bgdModel,fgdModel,5,cv2.GC_INIT_WITH_MASK)
10 
11 mask = np.where((mask==2)|(mask==0),0,1).astype('uint8')
12 img = img*mask[:,:,np.newaxis]
13 plt.imshow(img),plt.colorbar(),plt.show()

See the result below:

grabcut_mask.jpg
image

So that's it. Here instead of initializing in rect mode, you can directly go into mask mode. Just mark the rectangle area in mask image with 2-pixel or 3-pixel (probable background/foreground). Then mark our sure_foreground with 1-pixel as we did in second example. Then directly apply the grabCut function with mask mode.

Additional Resources

Exercises

  1. OpenCV samples contain a sample grabcut.py which is an interactive tool using grabcut. Check it. Also watch this youtube video on how to use it.
  2. Here, you can make this into a interactive sample with drawing rectangle and strokes with mouse, create trackbar to adjust stroke width etc.