Predicting Eye Fixations Under Distortion Using Bayesian Observers

2021/02/06 by Tu, Zhengzhong
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2102.03675

Abstract

Visual attention is very an essential factor that affects how human perceives visual signals. This report investigates how distortions in an image could distract human's visual attention using Bayesian visual search models, specifically, Maximum-a-posteriori (MAP) \citefindlay1982global\citeeckstein2001quantifying and Entropy Limit Minimization (ELM) \citenajemnik2009simple, which predict eye fixation movements based on a Bayesian probabilistic framework. Experiments on modified MAP and ELM models on JPEG-compressed images containing blocking or ringing artifacts were conducted and we observed that compression artifacts can affect visual attention. We hope this work sheds light on the interactions between visual attention and perceptual quality.

Related

• The Effect of Distortions on the Prediction of Visual Attention
• Maps of Visual Importance
• Visual Attention is Beyond One Single Saliency Map
• Modeling human visual search: A combined Bayesian searcher and saliency map approach for eye movement guidance in natural scenes
• Guiding human gaze with convolutional neural networks