The invention discloses a hand posture recognition system based on human body surface myoelectricity signals. The hand posture recognition system based on human body surface myoelectricity signals comprises a data acquiring module, a data processing module and a display module, wherein the data acquiring module consists of an analog signal acquiring circuit power supply unit, an analog signal acquiring circuit unit, a sensor unit, a digital signal acquiring circuit power supply unit and a digital signal acquiring unit, and is mainly used for acquiring the surface myoelectricity signals; the data processing module consists of a filter unit, a starting point and end point judgment unit, a feature extracting unit and a mode recognition unit, and is mainly used for processing data; and the display module consists of a picture unit and a voice unit, and is mainly used for displaying an action recognition result. The hand posture recognition system based on human body surface myoelectricitysignals is reasonable in structural design; the cost is saved; myoelectricity signals of muscles of arms of human bodies are acquired by multiple channels; hand actions can be rapidly and accurately recognized; and a great effect of promoting electromechanical control by the surface myoelectricity signals is achieved.