Method for extracting and identifying characteristics of electro-ocular signal

Abstract

The invention relates to a method for extracting and identifying characteristics of an electro-ocular signal, which is characterized by comprising three stages, namely pretreatment of the electro-ocular signal, extraction of characteristic parameters of the electro-ocular signal and mode identification of the electro-ocular signal, wherein in the pretreatment stage, endpoint detection and bandpass filtering on the electro-ocular signal are carried out; in the characteristic parameter extraction stage, frame separation and windowing on the electro-ocular signal are carried out, and an electro-ocular characteristic parameter sequence changed along with time after converting the continuous electro-ocular signal into a plurality of sections of short-time electro-ocular signals is extracted; and in the mode identification stage, similarity comparison between the input electro-ocular characteristic parameter sequence and each template of a template base sequentially through a dynamic time normalization method is carried out so as to judge the corresponding eye movement of the operator. The method has the characteristics of high identification accuracy of the electro-ocular signal, certain antijamming capacity, strong application value and the like.

Description

technical field [0001] The invention relates to the interdisciplinary field of biomedicine and informatics, and more specifically relates to a feature extraction and recognition method for electrooculogram signals. Background technique [0002] Eyes are the windows of the soul, through which we can explore the laws of many psychological activities of people. Human information processing relies heavily on vision, and about 80% to 90% of information from the outside world is obtained through human eyes. Therefore, the study of eye movement is considered to be the most effective method in the study of visual information processing. Many domestic and foreign studies on oculoelectricity have proved that the corneal part of the eyeball is a positive electrode, and the retina part is a negative electrode. This retinal electrostatic potential signal that exists between the retinal pigment epithelium and photoreceptor cells is called electro-oculogram , that is, the EOG signal. Wh...

AI Technical Summary

Problems solved by technology

Since the above-mentioned electro-oculogram feature extraction and electro-oculogram signal recognition algorithms do not fully consider the variability of electro-oculogram signals, that is, when the detection electrode positions are different or different users perform the same eye movements, the amplitude, peak value, and eyeball output of electro-oculogram signals may vary. The parameters such as rotation speed are different; on the other hand, because the oculoelectric signal is easily interfered by external signals such as static electricity and electromagnetic noise of electric objects, as well as noise such as human body electromyographic signals and electrocardiographic signals, the selection of the detection threshold determines the Algorithm recognition accuracy

In actual use, an ideal detection threshold is often difficult to obtain, so the above method cannot guarantee the accuracy of electrooculogram signal recognition

[0005] 2. Cannot be used under noisy conditions

When the electrodes are in poor contact or are subject to strong external noise electromagnetic interference, the above algorithm cannot identify the electro-oculogram signal based on the extracted features, which leads to the failure of the algorithm

Images