SEQUENTIAL IMAGE ANALYSIS USING PULSE COUPLED NEURAL NETWORKS FOR PRE-PROCESSING

摘要

The more friendly communication can be promoted between the human and computer if the function of gesture recognition is implemented to the computer system as the input interface along with the keyboards and mice. We propose a mouse-like function for estimating hand shape from input images with a monocular camera, with which a computer user feels no restraint or awkwardness. Our system involves conversion of sequential images from Cartesian coordinates to log-polar coordinates. Pulse Couple Neural Networks are used to extract the hand region, because PCNN has superior segmentation ability. Recognition of the hand shape is carried out by the competitive neural network using higher order local autocorrelation features of log-polar coordinate space. Mouse-like functions are realized with the hand shape and motion trajectory. Compared to conventional Cartesian coordinates, conversion to log-polar coordinates enables us to reduce image date and computation time, remove the variability by the scaling, and improve antinoise characteristics.