Sign Language Recognition Using Temporal Classification
This work addresses sign language translation for users of gesture-based devices, but it is incremental as it builds on existing temporal classification techniques without introducing major innovations.
The paper tackled sign language recognition from temporal data using devices like the Myo armband, achieving reasonable performance with baseline models on high-quality data but requiring more sophisticated temporal classification methods for lower-quality data.
Devices like the Myo armband available in the market today enable us to collect data about the position of a user's hands and fingers over time. We can use these technologies for sign language translation since each sign is roughly a combination of gestures across time. In this work, we utilize a dataset collected by a group at the University of South Wales, which contains parameters, such as hand position, hand rotation, and finger bend, for 95 unique signs. For each input stream representing a sign, we predict which sign class this stream falls into. We begin by implementing baseline SVM and logistic regression models, which perform reasonably well on high quality data. Lower quality data requires a more sophisticated approach, so we explore different methods in temporal classification, including long short term memory architectures and sequential pattern mining methods.