Image emotion classification method based on ResNet-GCN network

Abstract

The invention discloses an image emotion classification method based on a ResNet-GCN network. The method includes following steps: (1) designing an image emotion classification network formed by a front part structure ResNet-50 network and a rear part structure GCN network; (2) designing an image emotion classification framework including one image emotion classification network ResNet-GCN and onesupport vector classifier used for deciding fusion network characteristics; (3) performing substantial main body extraction and pyramid cutting on an original image; (4) training the image emotion classification network; (5) testing the image emotion classification framework; and (6) performing classification by employing the trained image emotion classification framework by a user image to realize image emotion classification. According to the method, an image emotion classification result is in accordance with the mankind emotion standard, human participation is avoided in a determination process, and automatic image emotion classification of a machine is realized.

Description

technical field [0001] The invention relates to the technical field of image classification, in particular to an image emotion classification method based on a ResNet-GCN network. Background technique [0002] We are susceptible to all kinds of emotions stimulated by visual content, especially images. Image emotion classification is to classify images according to the human emotions aroused by images. The image emotions commonly used in the research are pleasure, awe, satisfaction, excitement, anger, disgust, fear, and sadness. Due to the complexity of images and the subjectivity of human emotions, it is a very challenging task to automatically realize image emotion classification by computer simulation of human high-level perception to judge image emotion. [0003] Existing image sentiment classification methods have gone through two stages: traditional manual feature method and deep learning method. Compared with the traditional manual feature method, the deep learning ...

AI Technical Summary

Problems solved by technology

The network blindly learns the characteristics of different factors of the image, and lacks specific analysis of the relevant factors that affect the emotional expression of the image, which not only fails to significantly improve the performance of image emotion classification, but also increases the complexity of the network and reduces the generalization ability of the network.

[0005] Existing image emotion classification methods lack targeted model design and cannot effectively express global and local image information comprehensively

Images