Beyond pixels: Exploiting camera metadata for photo classification
| Autor: | Jiebo Luo, Matthew Boutell |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Pixel
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Bayesian network Class (biology) Image (mathematics) Domain (software engineering) Metadata Discriminative model Artificial Intelligence Signal Processing Computer vision Computer Vision and Pattern Recognition Artificial intelligence business Software |
| Zdroj: | Pattern Recognition. 38:935-946 |
| ISSN: | 0031-3203 |
| DOI: | 10.1016/j.patcog.2004.11.013 |
| Popis: | 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 provide cues independent of the captured scene content that can be used to improve classification performance. We consider three problems, indoor-outdoor classification, sunset detection, and manmade-natural classification. Analysis of camera metadata statistics for images of each class revealed that metadata fields, such as exposure time, flash fired, and subject distance, are most discriminative for each problem. 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 three problems using content-based and metadata cues to demonstrate the efficacy of the proposed integrated scene classification scheme. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect