Contextual Identity Recognition in Personal Photo Albums
| Autor: | Dragomir Anguelov, Baris Sumengen, Salih Burak Gokturk, Kuang-Chih Lee |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
Markov random field
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Markov process Inference Pattern recognition Identity recognition Facial recognition system Expression (mathematics) symbols.namesake ComputingMethodologies_PATTERNRECOGNITION symbols Artificial intelligence business |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2007.383057 |
| Popis: | We present an efficient probabilistic method for identity recognition in personal photo albums. Personal photos are usually taken under uncontrolled conditions -the captured faces exhibit significant variations in pose, expression and illumination that limit the success of traditional face recognition algorithms. We show how to improve recognition rates by incorporating additional cues present in personal photo collections, such as clothing appearance and information about when the photo was taken. This is done by constructing a Markov random field (MRF) that effectively combines all available contextual cues in a principled recognition framework. Performing inference in the MRF produces markedly improved recognition results in a challenging dataset consisting of the personal photo collections of multiple people. At the same time, the computational cost of our approach remains comparable to that of standard face recognition approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|