The invention provides a rotary characteristic extraction method based on the gesture identification of an acceleration sensor, which comprises the following steps that: three-axis acceleration signals produced when a user writes in a three-dimensional space are respectively projected to a y-z plane, a z-x plane and an x-y plane to obtain three two-dimensional vectors, i.e. Ayz(t), Azx(t) and Axy(t), then the rotary characteristics, i.e. RFyz(i), RFzx(i) and RFxy(i) of the y-z plane, the z-x plane and the x-y plane are respectively extracted, and the extracted rotary characteristics RFyz(i), RFzx(i) and RFxy(i) are respectively encoded to obtain rotary characteristic codes Cyz, Czx and Cxy. The method extracts the novel rotary characteristics from the three-axis acceleration signals and the rotary characteristics can effectively express the change process of the clockwise rotation and the counterclockwise rotation of gesture motion when in writing, can conveniently realize a complete framework of the three-dimensional space writing digital identification algorithm based on the rotary characteristics by extracting according to the rotary characteristics provided by the invention so as to effectively identify three-dimensional writing characters based on the acceleration sensor.