Electromyographic signal gesture action recognition method based on texture features

Abstract

The invention relates to the technical field of biological signal recognition, in particular to an electromyographic signal gesture action recognition method based on texture features. The method comprises the steps of firstly collecting myoelectricity data under different gesture actions, secondly representing original myoelectricity data by using a cyclic gray-level co-occurrence matrix, then extracting texture features of corresponding position offset robustness according to the obtained cyclic gray-level co-occurrence matrix, finally extracting time domain features on the basis of the texture features; and inputting the obtained time domain features into a classifier for model training, and finally outputting a gesture action classification result. The method provided by the invention has great flexibility, can well solve the problem that the model precision is reduced due to the position offset of the sensor in practical application, and effectively improves the robustness of the myoelectricity man-machine interaction system.

Description

technical field [0001] The invention relates to the technical field of biosignal recognition, in particular to a texture feature-based gesture recognition method for electromyographic signals. Background technique [0002] Surface electromyography is the electrical signal of muscle activity collected from the surface of human skin, which contains rich information about body behavior and movement. Due to the characteristics of non-invasive signal acquisition and strong signal distribution, surface electromyography is widely used in human-computer interaction systems such as intelligent prosthetics, rehabilitation robots, power-assisted robots, and text input for amputee patients. Traditional EMG-based human-computer interaction methods mainly include: surface EMG signal preprocessing, feature extraction, feature selection, model training, and model tuning. However, the high-performance algorithms obtained in the ideal environment of the laboratory often cannot be directly ap...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the deficiencies of the prior art, the present invention provides a gesture recognition method based on texture features, which effectively solves the problem that the accuracy of gesture recognition decreases due to electrode offset during the gesture recognition process. , improve the robustness of the EMG human-computer interaction system, and greatly reduce the burden on users

Images