Trains a Hidden Markov Model to recognize American Sign Language words on a video. It then uses a Language Model to improve full sentence recognition. This is based on a Udacity project - I was able to achieve significantly better recognition (65% with just the HMM and 77% with the language model) than was expected in the class (40-50% recognition was required to pass).
-
Notifications
You must be signed in to change notification settings - Fork 1
Trains a Hidden Markov Model to recognize American Sign Language words on a video. I was able to achieve significantly better recognition (65% with just the HMM and 77% by adding a language model) than was expected in the Udacity class (40-50% recognition was required to pass).
mcleavey/sign-language-recognizer
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Trains a Hidden Markov Model to recognize American Sign Language words on a video. I was able to achieve significantly better recognition (65% with just the HMM and 77% by adding a language model) than was expected in the Udacity class (40-50% recognition was required to pass).
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published