Time-Domain Feature Parameter Extraction Algorithm of Pulse Wave Based on Morphological Features

Pulse wave’s Time-domain characteristics have clear physiological and pathological significance, are widely used in pulse recognition disease prediction. At present, for different forms of wave feature points, the accuracy time-domain point extraction algorithms varies greatly. Therefore, this paper proposes a algorithm based on morphological features. Firstly, is normalized averaged by using normalization correlation averaging methods. Secondly, main divided into two states: extreme non-obvious feature. The characteristic morphology dicrotic front three point, feature, fusion or disappearance. Finally, location range each determined, points identified curvature method difference method. experiment shows that can effectively identify common waves, which creates conditions effective subsequent relevant human information.