Abstract SpatialBoost extends AdaBoost to incorporate spatial reasoning. We demonstrate the effectiveness of SpatialBoost on the problem of interactive image segmentation. Our application takes as input a tri-map of the original image, trains SpatialBoost on the pixels of the object and the background and use the trained classifier to classify the unlabeled pixels. The spatial reasoning is introduced in the form of weak classifiers that attempt to infer pixel label from the pixel labels of surrounding pixels, after each boosting iteration. We call this variant of AdaBoost — SpatialBoost. We then extend the application to work with “GrabCut”. In GrabCut the user casually marks a rectangle around the object, instead of tediously marking a tri-map, and we pose the segmentation as the problem of learning with outliers, where we know that only positive pixels (i.e. pixels that are assumed to belong to the object) might be outliers and in fact should belong to the background.
SpatialBoost: Adding Spatial Reasoning to AdaBoost
Computer Vision – ECCV 2006 ; 7 ; 386-396
Lecture Notes in Computer Science ; 3954 , 7
2006-01-01
11 pages
Article/Chapter (Book)
Electronic Resource
English
SpatialBoost: Adding Spatial Reasoning to AdaBoost
British Library Conference Proceedings | 2006
|Incorporating posterior estimates into AdaBoost
British Library Online Contents | 2009
|Adding temporal reasoning to expert-system-building environments
Tema Archive | 1990
|AdaBoost-based face detection for embedded systems
British Library Online Contents | 2010
|Exploiting Universum data in AdaBoost using gradient descent
British Library Online Contents | 2014
|