Method for recognizing happiness degree of crowd based on deep learning

Abstract

The invention discloses a method for recognizing the happiness degree of a crowd based on deep learning. The method comprises: firstly classifying manually marked individual face images and normalizing image sizes to obtain a face happiness degree database and a face shielding degree database; separately dividing the face happiness degree database and the face shielding degree database into a training set and a verification set to train a convolution neural network; then identifying the happiness degree and the shielding degree of faces in an input group photo by using a trained network model; and finally calculating the happiness degree of the crowd in the image by using face happiness degree weighted way. The method analyzes the expression of the crowd in the image by using the deep learning, is more accurate compared with traditional methods of extracting PHOG and Gabor, and provides new ideas and approaches for crowd emotion recognition in the image.

Description

technical field [0001] The present invention relates to the field of image processing and pattern recognition, and relates to a crowd emotion recognition method, in particular to a crowd happiness recognition method based on deep learning. Background technique [0002] A lot of research on facial expression recognition can be seen in recent years, but few people pay attention to the emotions expressed by a group of people in the image. With the popularity of data sharing and the rise of social networking sites such as YouTube and Flickr, users upload hundreds of millions of social pictures and videos every day, such as parties, weddings, graduation banquets, etc. attended. Usually, these uploaded videos and images may contain one or more people, so learning about crowds is a critical step. [0003] For example, if it is necessary to guess the mood of people in a group photo of a group of people participating in a class reunion, it is still challenging to use the existing em...

AI Technical Summary

Problems solved by technology

In view of the wider application value, people have more and more interest in understanding the performance of human emotional attributes, but from the perspective of emotional analysis, the scene changes in images are still little attention in the field of affective computing.

At present, in terms of emotion recognition and analysis, it is generally aimed at a single person. Human facial expressions are divided into six basic expressions: happiness, surprise, disgust, anger, fear, and sadness. Few researchers are engaged in the classification and recognition of group expressions.

Images