Micro-expression recognition method based on peak frame and depth forest

Abstract

The invention discloses a micro-expression recognition method based on a peak frame and a depth forest. The method mainly relates to micro-expression peak frame positioning and micro-expression recognition by using a peak frame training depth forest model. The method comprises the steps of preprocessing a micro-expression sample, determining a peak frame by calculating a frequency, performing feature extraction by using a VGG-Face network, and performing micro-expression classification training and testing on a deep forest model. According to the method, the micro-expression peak frames are positioned as a training set, so that redundancy caused by general micro-expression frames with too low facial action intensity can be effectively avoided. A micro-expression peak frame data sample is small in scale, the characteristic that a depth forest has excellent performance under the condition of a small number of data samples is combined, a training depth forest model is selected to recognize micro-expressions, and the accuracy and efficiency are improved.

Description

technical field [0001] The invention relates to the field of deep learning and pattern recognition, in particular to a micro-expression recognition method based on peak frame and deep forest. Background technique [0002] Micro-expressions express the true emotions that people try to cover up and hide. They are a set of time-continuous image sequences, and the duration is generally between 250ms and 500ms. Research on micro-expressions can help reveal people's psychological changes in specific scenarios, such as revealing Prisoners lie, assess people's inner emotional state, and then promote the development of criminology, psychology and other aspects. [0003] At present, the research methods of micro-expression recognition are mainly concentrated in the field of traditional machine learning and deep neural network; the recognition rate of traditional machine learning methods is generally not high enough to meet the actual application requirements; deep neural network needs...

AI Technical Summary

Problems solved by technology

[0003] At present, the research methods of micro-expression recognition are mainly concentrated in the field of traditional machine learning and deep neural network; the recognition rate of traditional machine learning methods is generally not high enough to meet the actual application requirements; deep neural network needs a large amount of training data during training, and Therefore, the deep neural network cannot be used for small-scale data tasks, but the number of data set samples currently used for micro-expression research is scarce; so the existing technology needs a peak-based method that can improve the accuracy and efficiency of micro-expression recognition. Micro-expression Recognition Method Based on Frame and Deep Forest

Images