Abstract:
Sign language recognition has become
an important research area in assistive technology,
with machine learning and computer vision
providing opportunities to support communication
between deaf or hard-of-hearing people and the
wider community. Existing studies have
investigated different approaches for recognizing
sign language gestures from images and video,
including convolutional neural networks (CNNs),
long short-term memory (LSTM) networks,
support vector machines (SVMs), wearable devices,
depth cameras, and mobile-based systems.
However, much of the existing research focuses on
widely studied sign languages or Sinhala Sign
Language, while research specifically related to Sri
Lankan Tamil Sign Language (TSL) remains
limited. Therefore, this systematic literature review
examines existing machine learning and computer
vision approaches for sign language recognition and
translation, with particular attention to their
relevance to TSL. A total of 18 studies were
reviewed based on the sign language considered,
type of input data, recognition task, machine
learning technique, dataset, translation approach,
hardware requirements, and reported limitations.
The review shows that CNN-based approaches are
commonly used for visual gesture recognition, while
LSTM and other sequence-based approaches have
been applied to continuous sign recognition. SVM-
based methods and specialized hardware such as
depth cameras and wearable devices have also been
reported. However, the reviewed studies indicate
limited availability of TSL-specific datasets and
limited research on continuous TSL recognition,
Tamil language translation, and low-cost real-time
implementation. These findings indicate the need
for further TSL-specific research, particularly the
development of suitable datasets and the evaluation
of computer vision and machine learning
approaches using TSL data. The findings of this
review provide a basis for future research on
practical TSL recognition and translation systems
using affordable camera-based devices.
