Micro-expression recognition robot and control method thereof

Abstract

The invention discloses a micro-expression recognition robot. The robot comprises: an expression collector which collects and determines an expression image of a tested person; a micro-expression recognizer connected with the expression collector and used for recognizing five-sense-organ baseline data of the tested person according to the real-time stress expression information and the expressiondata of the tested person; and a micro-expression analyzer connected with the micro-expression recognizer and used for classifying the five-sense-organ baseline data of the tested person to obtain a micro-expression recognition result. The five-sense-organ baseline data of the tested person are recognized according to the real-time stress expression information and the expression data of the tested person, and the recognition effect is good. Another purpose of the invention is to provide a micro-expression recognition method, which can acquire and determine the expression image of the tested person and determine the micro-expression state of the user based on the BP neural network, so that the matching process is simplified, and the quick recognition of the micro-expression is realized.

Description

technical field [0001] The invention relates to the field of micro-expression recognition, in particular to a micro-expression recognition robot and a control method thereof. Background technique [0002] Micro-expression is a very short-lived, uncontrollable facial expression leaked when humans try to suppress or hide their true emotions. It is an effective clue for lie recognition and is mainly used in the fields of security, justice, clinical and education. [0003] At present, when micro-expressions are recognized, a micro-expression library that has been marked with various expression categories is preset, and then the distance value between the micro-expression image to be recognized and each preset micro-expression in the expression library is determined. When the distance value is greater than When a certain preset value is selected, it is determined that the expression category of the preset micro-expression corresponding to the distance value is the expression cate...

AI Technical Summary

Problems solved by technology

[0004] However, in the current application stage, it can only be applied to the low recognition of a single target. In the field of education, especially in the application of online courses, it is necessary to recognize and detect the expressions of student groups. The calculation workload is heavy, the recognition efficiency is low, and it cannot be transmitted in time. Feedback recognition results

Images