Abstract | ||
---|---|---|
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 ap- parently 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 classi- fiers 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. |
Year | Venue | Keywords |
---|---|---|
2008 | BMVC | random forest,spatial context,discrimination learning,machine learning |
Field | DocType | Citations |
Histogram,Nearest neighbour,Pattern recognition,Texton,Computer science,Segmentation,Object Class,Artificial intelligence,Spatial contextual awareness,Random forest,Classifier (linguistics),Machine learning | Conference | 77 |
PageRank | References | Authors |
4.94 | 19 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Florian Schroff | 1 | 757 | 32.72 |
Antonio Criminisi | 2 | 6801 | 394.29 |
Andrew Zisserman | 3 | 45998 | 3200.71 |