Abstract:
This paper proposes new real time color recognition features, i.e., extracting primary colors for the purpose of vision-based human–computer interaction. Vision-based human–computer interaction could be achieved by analyzing segmented primary color regions. However, one of the challenges of color-based target tracking is that color distributions would change in different lighting conditions. This paper presents our investigation of color-based image segmentation, non-stationary color-based target tracking, color based mouse pointer, color based virtual music instruments, and color based virtual calculator. Our experiments show that Red, green and blue are the default color used for recognition process. Live video is captured from camera and the video is converted into number of frame images. This algorithm should monitor and process the every frame from the live video. Microphone and camera is used as an input devices. Here image processing is done through MATLAB for color recognition process.

Keywords: human computer interaction, color recognition, color segmentation, real time video