2004 · 66 citations · 15 references
ComputingComputer ScienceComputer VisionMachine LearningSensor FusionCamera ModelsImage ClassificationObject DetectionObject RecognitionScene ClassificationScene UnderstandingBayesian Feature FusionBayesian FusionBayesian Network AnalysisBayesian Network IntegrationImage-based Scene RecognitionIndoor Scene ClassificationOutdoor Scene ClassificationSemantic Scene Understanding
Semantic scene classification based only on low-level vision cues has had limited success on unconstrained image sets. On the other hand, camera metadata related to capture conditions provides cues independent of the captured scene content that can be used to improve classification performance. We consider two problems: indoor-outdoor classification and sunset detection. Analysis of camera metadata statistics for images of each class revealed that metadata fields, such as exposure time, flash fired, and subject distance, is most discriminative for both indoor-outdoor and sunset classification. A Bayesian network is employed to fuse content-based and metadata cues in the probability domain and degrades gracefully, even when specific metadata inputs are missing (a practical concern). Finally, we provide extensive experimental results on the two problems, using content-based and metadata cues to demonstrate the efficacy of the proposed integrated scene classification scheme.
15
Indoor-outdoor image classification
Martin Szummer, Rosalind W. Picard · 2002 · 639 citations
A unified framework for semantics and feature based relevance feedback in image retrieval systems
Ye Lü, Chunhui Hu, Xingquan Zhu et al. · 2000 · 240 citations
Using two-class classifiers for multiclass classification
David M. J. Tax, Robert P. W. Duin · 2003 · 196 citations