Convolutional neural network emotion image classification method combining emotion category attention loss

Abstract

The invention discloses a convolutional neural network emotion image classification method combining emotion category attention loss, and relates to the technical field of intelligent media calculation and computer vision. The method comprises the following steps: firstly, performing category weight calculation on a training sample to obtain an emotion category attention weight vector; secondly, modifying a final classification layer and a loss function of the convolutional neural network according to the emotion category number and the emotion category attention loss; then preprocessing the training sample and then transmitting the preprocessed training sample into a network, so that the network achieves convergence after iterative updating of parameters by a loss function and an optimizer, and training is completed; and finally, sending the preprocessed test image into a network, and calculating the emotion image classification accuracy of the obtained model and the prediction category of the model for the test emotion image. According to the convolutional neural network emotion image classification method, when sentiment classification is carried out on the sentiment image through the convolutional neural network, a classification result more conforming to data set sample distribution characteristics can be obtained in a self-adaptive mode, and training and using of a sentiment classification algorithm in different actual application scenes are facilitated.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to a convolutional neural network emotional image classification method combined with emotional category attention loss. Background technique [0002] With the development of social media, people are more and more inclined to record and share their emotions by posting image information on the Internet. These pictures containing emotional information often also contain the publisher's emotional tendency and attitude towards a certain type of thing. Understanding the attitudes of user groups by learning people's emotional trends from massive images plays an important role in product recommendation, public opinion analysis, and social media management. Therefore, how to use computer algorithms to efficiently and automatically identify and analyze a large number of images containing emotional information is an urgent problem to be solved. [0003] Earlier sentiment analysis meth...

AI Technical Summary

Problems solved by technology

Although these studies consider the intra-bundle distance, there is no targeted loss function design for sentiment categories with unbalanced sample sizes, which is not enough in real social media environments.

In a real social media environment, the number of emotional images cannot be evenly distributed by category

This will make the commonly trained model unable to consider each emotion category in a targeted manner, resulting in the loss of classification performance.

Images