2019 42nd International Conference on Telecommunications and Signal Processing (TSP)
The TSP 2019 Conference is organized by seventeen universities from Czech Rep., Hungary, Turkey, Taiwan, Japan, Slovak Rep., Spain, Bulgaria, France, Slovenia, Croatia, Greece, and Poland, for academics, researchers, and developers and it serves as a premier annual international forum to promote the exchange of the latest advances in telecommunication technology and signal processing. The aim of the conference is to bring together both novice and experienced scientists, developers, and specialists, to meet new colleagues, collect new ideas, and establish new cooperation between research groups from universities, research centers, and private sectors from the whole Europe, America, Asia, Australia, and Africa. The international expansion motivates the organizers in their effort to providing a platform for exchanging information and experience to help to improve the level and extent of scientific cooperation between university students, academics, and employees of research centers.
In this paper, we compare several real-time sign language dactyl recognition systems and present a new model based on deep convolutional neural networks. These systems are able to recognize Russian alphabet letters presented as static signs in Russian Sign language used by people from deaf community. In such an approach, we recognize words from Russian natural language presented by consequent hand gestures of each letter. We evaluate our approach on Russian (RSL) sign language, for which we collect our own dataset and evaluate dactyl recognition.