Time-segmentation- and Position-free Recognition from Video of Air-drawn Gestures and Characters.
Yuki NitsumaSyunpei ToriiYuichi YaguchiRyuichi OkaPublished in: ICPRAM (2014)
Keyphrases
- character segmentation
- video segmentation
- sign recognition
- handwritten characters
- automatic recognition
- sign language
- character recognition
- gesture recognition
- printed characters
- image parsing
- hand gestures
- human activities
- recognition rate
- temporal segmentation
- text detection
- video sequences
- video data
- level set
- image segmentation
- numeral strings
- spoken words
- multiscale
- scene text
- medical images
- segmentation algorithm
- text lines
- video frames
- multimedia
- recognition algorithm
- video streams
- traffic signs
- video analysis
- hidden markov models
- printed documents
- hand written
- segmentation method
- video content
- video scene
- object recognition
- feature extraction
- objects in video sequences
- document analysis
- visual input
- video objects
- optical character recognition
- license plate
- handwritten words
- human robot interaction
- key frames
- bounding box