Abstract | ||
---|---|---|
In this paper, we propose a novel method for spatial context modeling toward boosting visual discriminating power. We are particularly interested in how to model high-order local spatial contexts instead of the intensively studied second-order spatial contexts, i.e., co-occurrence relations. Motivated by the recent success of random forest in learning discriminative visual codebook, we present a spatialized random forest (SRF) approach, which can encode an unlimited length of high-order local spatial contexts. By spatially random neighbor selection and random histogram-bin partition during the tree construction, the SRF can explore much more complicated and informative local spatial patterns in a randomized manner. Owing to the discriminative capability test for the random partition in each tree node's split process, a set of informative high-order local spatial patterns are derived, and new images are then encoded by counting the occurrences of such discriminative local spatial patterns. Extensive comparison experiments on face recognition and object/scene classification clearly demonstrate the superiority of the proposed spatial context modeling method over other state-of-the-art approaches for this purpose. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/TIP.2012.2222895 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
spatial context,random forest,tree construction,visual codebook,image coding,informative high-order local spatial patterns,face recognition,visual discriminating power boosting,srf approach,spatially random neighbor selection,spatialized random forest approach,object classification,learning (artificial intelligence),second-order spatial contexts,image classification,tree node split process,random histogram-bin partition,discriminative local spatial patterns,discriminative visual codebook learning,high-order local spatial context modeling,object-scene classification,learning artificial intelligence | Decision tree,Computer science,Artificial intelligence,Random forest,Contextual image classification,Spatial ecology,Discriminative model,Computer vision,Pattern recognition,Boosting (machine learning),Spatial contextual awareness,Machine learning,Codebook | Journal |
Volume | Issue | ISSN |
22 | 2 | 1941-0042 |
Citations | PageRank | References |
3 | 0.38 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bingbing Ni | 1 | 1421 | 82.90 |
Shuicheng Yan | 2 | 767 | 25.71 |
Meng Wang | 3 | 2097 | 53.43 |
Ashraf A. Kassim | 4 | 1164 | 97.26 |
Qi Tian | 5 | 6443 | 331.75 |