Finger spelling recognition using neural network with pattern recognition model
Megumi Shimada, Shōichi Iwasaki, Toshiyuki ASAKURA · Society of Instrument and Control Engineers of Japan · 2003
This research is concerned with a human computer interface in an image and a gesture recognition of finger spelling using neural network (NN). In this paper, a new algorithm that recognize finger spelling image using NN with pattern recognition model (NN-PRM) is proposed. NN-PRM is applied to Japanese Kana finger spelling recognition. Through experimental results, it is shown that the algorithm proposed here is sufficiently effective for finger spelling recognition of static and motion images.