Semantic position recognition and visual landmark detection with invariant for human effect.
Yuuji IshikooriHirokazu MadokoroKazuhito SatoPublished in: SII (2017)
Keyphrases
- landmark detection
- visual processing
- visual perception
- visual learning
- object recognition
- high level
- human visual
- recognition rate
- recognition accuracy
- human activities
- semantically relevant
- visual attributes
- visual information
- invariant moments
- natural language
- feature extraction
- visual search
- recognition process
- human arm
- human subjects
- cognitive map
- static images
- semantic content
- computer vision
- semantic similarity
- affine transformation
- visual features
- semantic relationships
- recognition algorithm
- visual saliency
- semantic annotation
- action recognition
- human gait
- semantic web
- scan path
- domain specific
- pattern recognition
- metadata