Object Class Segmentation using Random Forests
Florian Schroff, Antonio Criminisi, Andrew Zisserman · British Machine Vision Conference (BMVC) · 2008
This work investigates the use of Random Forests for class based pixel-wise segmentation of images. The contribution of this paper is three-fold. First, we show that apparently quite dissimilar classifiers (such as nearest neighbour matching to texton class histograms) can be mapped onto a Random Forest architecture. Second, based on this insight, we show that the performance of such classifiers can be improved by incorporating the spatial context and discriminative learning that arises naturally in the Random Forest framework. Finally, we show that the ability of Random Forests to combine multiple features leads to a further increase in performance when textons, colour, filterbanks, and HOG features are used simultaneously. The benefit of the multi-feature classifier is demonstrated with extensive experimentation on existing labelled image datasets. The method equals or exceeds the state of the art on these datasets. 1
Cited by 239 works. doi:10.5244/c.22.54
Authors
References
- Random Forests
- C4.5: Programs for Machine Learning
- Rapid object detection using a boosted cascade of simple features
- Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
- Shape Quantization and Recognition with Randomized Trees
- TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation
- Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
- Sharing features: efficient boosting procedures for multiclass object detection
- Object categorization by learned universal visual dictionary
- Semantic texton forests for image categorization and segmentation