Image transform bootstrapping and its applications to semantic scene classification

Authors:
Jiebo Luo;M. Boutell;R. T. Gray;C. Brown
Affiliations:
R&D Labs., Eastman Kodak Co., Rochester, NY, USA;-;-;-
Venue:
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Year:
2005

Citing 0
Cited 7

Automatic image annotation by incorporating feature hierarchy and boosting to scale up SVM classifiers

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Naked image detection based on adaptive and extensible skin color model

Pattern Recognition
Probabilistic optimized ranking for multimedia semantic concept detection via RVM

CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Scene classification using multiple features in a two-stage probabilistic classification framework

Neurocomputing
Local autocorrelation of similarities with subspaces for shift invariant scene classification

Pattern Recognition
Bootstrapping Boosted Random Ferns for discriminative and efficient object classification

Pattern Recognition
Local co-occurrence features in subspace obtained by KPCA of local blob visual words for scene classification

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The performance of an exemplar-based scene classification system depends largely on the size and quality of its set of training exemplars, which can be limited in practice. In addition, in nontrivial data sets, variations in scene content as well as distracting regions may exist in many testing images to prohibit good matches with the exemplars. Various boosting schemes have been proposed in machine learning, focusing on the feature space. We introduce the novel concept of image-transform bootstrapping using transforms in the image space to address such issues. In particular, three major schemes are described for exploiting this concept to augment training, testing, and both. We have successfully applied it to three applications of increasing difficulty: sunset detection, outdoor scene classification, and automatic image orientation detection. It is shown that appropriate transforms and meta-classification methods can be selected to boost performance according to the domain of the problem and the features/classifier used.