A method of using the support vector machine combining with the bionic-six-hand models to optimize infrared motion control apparatus gesture recognition is proposed in this paper. The space gesture information is collected, then the gesture eigenvector is extracted by the bionic-six-hand models, and the support vector machine is used for the classification and proofread of the data, the kernel function is introduced to map the low-dimensional space un-separable information into the high-dimensional space to realize detachable linearity. The experimental results show that the infrared somatosensory device using the support vector machine algorithm can recognize the hand gestures effectively and reduce the load of communication transmission.