This paper proposes an EMG recognition system of grasping force on the basis of the pattern recognition, which can classify the surface electromyography (sEMG) signals from 2 electrodes and recognize the grasping force. Ten characteristics in time domain and frequency domain are chosen as the primary features to combine feature sets, to obtain an optimal feature set. The linear discriminant analysis (LDA) is used to reduce the dimension of the features vector to a one-dimensional vector matrix, and pattern recognition to classify and recognize it. In online recognition, to obtain continuous recognition values, the quadratic polynomial fitting is utilized to find the relationship between the one-dimensional vector matrix and grasping forces.