Visual perception identification system

Abstract

The invention provides a visual perception identification system, which is characterized by carrying out signal amplification on skin image changes of a person in a high-sampling-rate video image; obtaining wave type description and positioning of the heart rate and breathing change signals through a series of filtering and digital signal processing and according to a volume pulse wave description method, and obtaining physiological parameters of HR, HRV, BR and OS and the like, and establishing nonlinear feature engineering; carrying out data modeling by utilizing a neural network; carrying out classification on correspondence relation between psychological statuses and physiological indicators by utilizing weavlet and SVM and the like; and obtaining more obvious distinction degree through Lyapunov exponents in a two-dimensional coordinate space, wherein the distinction degree can be used for classification of positive emotions and negative emotions. The system can realize more classification dimensions under the condition that the acquisition data increases continuously, and has better evolvability.

Description

technical field [0001] The present invention relates to the field of signal and information processing, and more specifically, to a visual perception recognition system. Background technique [0002] With the advancement of computer technology, human-computer interaction is constantly developing in the direction of humanization and simplification, and non-contact gesture interaction has gradually become an important way of human-computer interaction. Compared with contact operation methods such as mouse, keyboard, touch screen, etc., non-contact gesture interaction is more in line with human's natural behavior. In recent years, with the development of computer vision and image processing technology, gestures based on machine vision and computer interaction are becoming the mainstream of new human-computer interaction methods. However, the existing gesture interaction experience is not ideal. How to overcome the interference of environmental factors, accurately obtain gestur...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the foregoing problems, the object of the present invention is to provide a visual perception and recognition system that can comprehensively and intuitively evaluate the corresponding relationship between psychology and physiology through non-contact intelligent human-computer interaction.