Video-based nonlinear online expression pre-detection method and device

Abstract

The invention discloses a video-based nonlinear online expression pre-detection method and device. The method includes: preprocessing video data, extracting feature information of each frame of image; extracting video clips of different lengths from training samples, constructing Non-linear mapping between fragments and detection function values; the representation of fragments is based on multi-instance learning, fully mining effective expression information, and constructing a constraint pair for every two video fragments according to the size of the mapping value to obtain training data; at each moment , use all the constraints of the current sample to update the model OKMEFD, by minimizing the experience loss and model complexity on the current training data set, use the stochastic gradient descent algorithm to optimize the model, obtain the online update criterion of the model, and further obtain each moment The nonlinear expression pre-detection function. The pre-detection method is as follows: read the data of the test sample frame by frame and output the corresponding detection value, and when the value is greater than the set threshold, it is considered that the expression event is pre-detected. The invention realizes the pre-detection before the end of the facial expression video, and effectively improves the timeliness of facial expression recognition.

Description

technical field [0001] The invention relates to an expression pre-detection method and device, belonging to the interdisciplinary technical fields of facial expression recognition, video processing, and event pre-detection. Background technique [0002] After entering the 21st century, with the rapid development of artificial intelligence technology, computer technology and related disciplines, the demand for human-computer interaction has become increasingly strong. Faced with the deepening of related research and huge application prospects, facial expression recognition based on video In the past ten years, it has become a research hotspot in the field of artificial intelligence and machine learning, and has made great progress. Although related algorithms emerge in endlessly, many theories are still incomplete, and there are almost no mature commercial results. There is a process for the generation and disappearance of expressions. The traditional recognition method is t...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is the complexity of the facial expression pre-detection problem. The present invention proposes a video-based nonlinear online facial expression pre-detection method OKMEFD (online kernel multi-instance learning for early facial expression detection), which further improves the pre-facial expression detection. Validity of detection

Images