Forming method and system of facial expression intensity calculation model

Abstract

The invention provides a forming method and a system of a facial expression intensity calculation model. The model is used for estimating the facial expression intensity under expression classification. The method comprises the steps of acquiring an expression database firstly, preprocessing image data in the expression database, extracting the data of a face part, performing feature extraction inthe three modes of face geometric features, local binary patterns and Gabor wavelet transform respectively, training data outputted in the previous step respectively in the full-supervision mode, thesemi-supervised mode and the non-supervision mode so as to obtain the relation between a feature and a facial expression intensity, respectively adopting trained data as the input of an ordinal random forest algorithm to train the data and respectively obtain facial expression intensity calculation sub-models, and forming a final facial expression intensity calculation model according to each ofthe sub-models. According to the invention, the facial expression intensity calculation model under the expression classification is trained by means of the database. The model is used for processingimage data, so that the intensity under the trained expression classification can be obtained.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to facial expression processing, and more specifically, to a method and system for forming a facial expression intensity calculation model. Background technique [0002] With the advancement of image processing technology, there are many methods that can recognize facial expressions based on the collected facial images, and classify the expressions: such as divided into happy, sad and intermediate states, and then divided into excited, calm, or Divided into doubts, fears, sadness, surprise and so on. There are many ways to classify, but currently these methods can only roughly classify expressions, and cannot know the specific intensity of the expression classification, such as how happy, how sad, etc., that is, the expression strength is not estimated based on expression recognition. Contents of the invention [0003] The technical problem to be solved by the present inve...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that, in view of the technical defect that the above-mentioned current method can only roughly classify ...

Images