Vision-Based Static Hand Gesture Recognition Using Support Vector Machines

Given that advances in technology have increased rapidly over the past few years, developing a vision-based recognition system that could aid in the interaction between the Deaf and the hearing does not sound that far-fetched anymore. We can distinguish between two categories of hand gestures, namely static and dynamic. A static gesture is a particular hand configuration and pose represented by a single image. A dynamic gesture is a moving gesture, represented by a sequence of images. This makes signed language a good test case for the classification of gestures, since each gesture is assigned a particular meaning. This paper will focus on the development of a system that will recognise static hand images against complex backgrounds based on South African Sign Language (SASL). A Support Vector Recognition system will be used to classify hand postures as gestures, due to its high generalization performance without the need to add apriori knowledge, even when the dimensions of the input space is very high.