Image Emotion Recognition Based on Deep Neural Network

Bo Li, Chen Guo, Hui Ren · 2018 IEEE International Conference of Safety Produce Informatization (IICSPI) · 2018

Images can convey rich semantics and induce various emotions to viewers. Several studies have been introduced recently that apply the deep learning technology to predict image emotion. In this paper, by extracting and combing the different levels of features, we build an emotion classification model based on feed forward deep neural network to classify image emotion. Experiments confirm the effectiveness of our network in predicting the emotion of images.

Read the paper · More papers on PaperTik