Real-time video emotion analysis method and system based on deep learning

Abstract

The invention discloses a real-time video emotion analysis method and system based on deep learning. The analysis method comprises the following steps of S1, obtaining a training data set; S2, recognizing microexpressions of the training data set through an algorithm based on a deep neural network, performing screening, and outputting 8 kinds of expression predicating values, wherein 8 kinds of expressions comprise a gentle expression, a happy expression, an amazed expression, a sad expression, an angry expression, a disgusted expression, a fear expression and a despised expression; S3, predicating shot human expressions through a heart rate algorithm, and obtaining corresponding heart rate values; and S4, comparing the heart rate values obtained in the step S3 with the expression predicating values obtained in the step S2, and outputting the expressions the same as the heart rate values obtained in the step S3. According to the real-time video emotion analysis method and system basedon deep learning disclosed by the invention, human face recognition in machine vision and an image classification algorithm are applied to detection of microexpressions and the heart rate, recognitionof the microexpressions is realized through the deep learning algorithm, and the real-time video emotion analysis method and system based on deep learning can be applied to the clinical field, the juridical field and the security field.

Description

technical field [0001] The present invention relates to the technical field of sentiment analysis, and more specifically, to a real-time video sentiment analysis method and system based on deep learning. Background technique [0002] In today's society, thousands of passengers pass through the security checkpoints of subways, train stations, and airports every day, or enter and exit the country through border checkpoints, and security personnel need to interact with them to determine the authenticity of the content of the conversation. Identify individuals who may be at high risk to endanger the security of other individuals or the nation. It's almost impossible to do a job like this well. Because people's cognitive resources are limited, time is also limited, and the ability to identify lies is very limited, and its identification rate is only slightly higher than the probability level. It is impossible for security personnel to hold back this almost never-ending flow of ...

AI Technical Summary

Problems solved by technology

But its results are not recognized in judicial decisions because numerous studies have shown polygraph results to be unreliable

Images