3D gesture segmentation for word-level Arabic sign language using large-scale RGB video sequences and autoencoder convolutional networks.
Abdelbasset BoukdirMohamed BenaddyAyoub EllahyaniOthmane El MeslouhiMustapha KardouchiPublished in: Signal Image Video Process. (2022)
Keyphrases
- sign language
- sign recognition
- word level
- video sequences
- gesture recognition
- american sign language
- word segmentation
- english text
- hand gestures
- language independent
- handwritten documents
- hand tracking
- document images
- word recognition
- machine translation
- language identification
- n gram
- hidden markov models
- depth data
- image segmentation
- restricted boltzmann machine
- human computer interaction
- viterbi algorithm
- hand motion
- document analysis
- image analysis
- image processing
- hand gesture recognition
- sentence level
- computer vision
- video camera
- dynamic scenes
- human motion
- writer identification