Open AccessHuman eye-fixation prediction based on Convolutional Neural Network in RGB images
Author(s) -
Miao yue,
Li Wei,
LI Chunle
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1827/1/012020
Subject(s) - computer science , artificial intelligence , encoder , convolutional neural network , salience (neuroscience) , pattern recognition (psychology) , human visual system model , channel (broadcasting) , encoding (memory) , feature (linguistics) , computer vision , image (mathematics) , computer network , operating system , linguistics , philosophy
Using neural networks to simulate and predict human visual attention mechanism is a hot topic in the field of computer vision. In this paper, we propose an end-to-end encoder-decoder network architecture to predict the fixation mechanism of human eyes, which consists of modules composed of multiple convolutional layers with different expansion rates to capture multi-scale features in parallel. In addition, the attention module is added on the basis of the encoder network structure, and a self-attention mechanism is introduced to capture the visual feature dependency in the channel size, and the semantic interdependence in the channel dimension is modeled to predict the visual salience more accurately. In this paper, five data sets and selected examples are used to demonstrate the effectiveness of the proposed method. Our method achieves competitive and consistent results on multiple evaluation indicators on MIT1003 and CAT2000 datasets.