Automatic translation of sign language with multi-stream 3D CNN and generation of artificial depth maps.
Giulia Zanon CastroRúbia Reis GuerraFrederico Gadelha GuimarãesPublished in: Expert Syst. Appl. (2023)
Keyphrases
- sign language
- depth map
- multi stream
- depth information
- multi view
- gesture recognition
- d scene
- hidden markov models
- audio visual
- stereo matching
- three dimensional
- high quality
- input image
- image sequences
- sign recognition
- depth data
- view synthesis
- hand gestures
- high resolution
- stereo pair
- time of flight
- low resolution
- stereo camera
- image processing
- super resolution
- multi modal
- human computer interaction
- bitstream
- disparity map
- background subtraction
- input data