Microexpression recognition robot

Abstract

<p><span lang="EN-US">Following the development of big data, the use of microexpression technology</span><span lang="EN-US"> has become increasingly popular. The application of microexpressions has expanded beyond medical treatment to include scientific case investigations. Because microexpressions are characterized by short duration and low intensity, training humans to recognize their yields poor performance results. Automatically recognizing microexpressions by using machine learning techniques can provide more effective results and save time and resources. In the real world, to avoid judicial punishment, people lie and conceal the <span>truth for a variety of reasons. In this study, our primary objective was to develop a system for real-time microexpression recognition. We used FaceReader</span> as the retrieval system and integrated the data with an application programming interface to provide recognition results as objective references in real-time. Using an experimental analysis, we also attempted to determine the optimal system configuration conditions. In conclusion, the use of artificial intelligence is expected to enhance the efficiency of investigations.</span></p>

The use of artificial intelligence in interrogations: voluntary confession

“…Since the introduction of the Facial Action Coding System in 1976, which enabled the identification of microexpressions [21], and the emergence of deep learning in AI, substantial advancements have been made in the field of noncontact polygraphy. Currently, various deep learning frameworks, such as deep neural networks (DNNs), convolutional neural networks, and recurrent neural networks (RNNs), are used in image recognition, speech recognition, and bioinformatics.…”