Face microexpression recognition method based on video magnification and depth learning

Abstract

The invention provides a method for recognizing facial micro-expression based on video amplification and depth learning. The method comprises the following steps of: using a video amplification technique based on interference cancellation to amplify the motion amplitude of the micro-expression video data; the enlarged video data being divided into video frame images, and all image sequences belonging to micro-expression are extracted according to the micro-expression tags in the data set to form a new data set; facial clipping preprocessing being carried out on the processed video, and all video image sequences being uniformly clipped into 110*110 size gray-scale images; the new data after preprocessing being put into the convolution neural network model and trained to extract the micro-expression feature data to achieve the task of micro-expression recognition. The technical proposal provided by the invention enlarges the amplitude of the expression action through the video amplification operation of eliminating interference to the complete data set, and simultaneously introduces a neural network model for training, thereby effectively improving the accuracy rate of the micro expression recognition on the basis of the full classification of the emotion label.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a face micro-expression recognition method based on video amplification and deep learning. Background technique [0002] Micro-expression is a kind of extremely short-term facial expression with a small range of movement, usually lasting no more than 0.5 seconds. Micro-expression can more accurately express human psychological activities, and inner revealing and concealment can be expressed through micro-expression. Due to these characteristics of micro-expression, it has a wide application prospect in polygraph detection, clinical diagnosis, education and criminal investigation. [0003] At present, the methods for automatically recognizing micro-expressions based on computers are mainly divided into the following categories: recognition based on local binary pattern (LBP) and its improved method, detection and recognition based on op...

AI Technical Summary

Problems solved by technology

Various recognition and detection methods are still limited to the use of traditional technologies and methods to realize the tasks of micro-expressions, which require a large amount of calculation, time-consuming and poor universality. More importantly, due to the short duration of micro-expressions and small range of motion It is difficult for traditional technologies and methods to further improve the recognition accuracy, which has become the biggest bottleneck in the development of micro-expression recognition technology.

Images