A Speedy Brain-Computer Interface Combined with Computer Vision

Brain-computer interface (BCI) refers to the direct connection created between the human or animal brain and external equipment to realize the exchange of information between the brain and the equipment. This concept has existed for a long time, but it was not until the 1990s that phased results began to appear. the development of BCI is impressive. By decoding subjects’ electroencephalogram (EEG) signal, BCI provides a channel for communication between subjects’ brain and external devices. However, the interaction speed of current BCIs is relatively insufficient. To this end, we propose CV-BCI, a P300-based BCI combined with computer vision (CV). We recruit 10 participants in this study and ask all participants to finish the same tasks with CV-BCI and a traditional BCI speller. This study analyses the performance of the CV-BCI and BCI speller in accuracy, information transfer rate (ITR), and interaction speed. The experimental results suggest that the proposed CV-BCI surpasses BCI speller in interaction speed (about 6 s per object and 20 s per object respectively) while CV-BCI keeps comparable accuracy and ITR with BCI speller. This study probably proposes a more user-centric and speedy BCI approach, which promotes the development of BCI.