Revisiting GrabCut

Abhijit Sarkar
Spring 2014 ECE 6504 Probabilistic Graphical Models: Class Project
Virginia Tech



Grabcut [1] is a well-established background foreground segmentation tool. In its original form, grabcut uses the RGB color mixture model for both background and foreground. We want to test the algorithm with additional image qualities, say color in Luv space and using Textons.


We follow the original method mentioned in the Grabcut paper, where, the data terms are modeled using a Gaussian mixture model of the RGB cues, each for background and foreground. Each GMM is taken to be a full covariance Gaussian mixture with K components. We take k=6. The pairwise energy term is a function of the Euclidian color distance and a regularization term . We have used the original 50 image dataset from Grabcut paper and varied  from 0.1 to 1.1 in a step of 0.25 to calculate the recall and precision for each image. An average precision and recall is reported for each case. The same technique is followed three different cases.

1.     In the Luv color space

2.     Using RGB + Texton

3.     Using Luv  + Texton

The textons are calculated from the matlab implementation of [2]. We generate a independent texton vocabulary for each image and use them to generate a texton histogram to assign in the data term of the model. A similar experiment is performed for all the three cases as mentioned above. We have used the grabcut code from [1].


We have reported the average precision and average recall for each of the cases.

It can be noted that, The recall is not very much affected by different image cues. Although highest recall is achieved for  For precision, The original model performs better than other models. If we look at the precision recall values together, then we might conclude that, Use of RGB and Texton gives the best results.

Here are some of the results:

RGB + Textons



RGB + Textons

with RGB

LUV + Texton



For the face, Luv gives best result where using only RGB gives artifacts

Success with RGB

Failure with LUV + Texton





[1]       C. Rother, V. Kolmogorov, and A. Blake, "Grabcut: Interactive foreground extraction using iterated graph cuts," in ACM Transactions on Graphics (TOG), 2004, pp. 309-314.

[2]       Y. J. Lee and K. Grauman, "Object-graphs for context-aware visual category discovery," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 34, pp. 346-358, 2012.