Automatic metadata generation and video editing based on speech and image recognition for medical education contents.
Satoshi TamuraKoji HashimotoJiong ZhuSatoru HayamizuHirotsugu AsaiHideki TanahashiMakoto KanagawaPublished in: INTERSPEECH (2006)
Keyphrases
- image recognition
- metadata
- video editing
- medical education
- digital libraries
- image classification
- pattern recognition
- video data
- face recognition
- video segmentation
- video camera
- multimedia
- database
- video database
- databases
- neural network
- medical imaging
- learning objects
- structured data
- low cost
- high resolution
- feature extraction
- three dimensional
- image processing