The anatomy of a large-scale hypertextual Web search engine
WWW7 Proceedings of the seventh international conference on World Wide Web 7
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Edge Detection with Embedded Confidence
IEEE Transactions on Pattern Analysis and Machine Intelligence
A user attention model for video summarization
Proceedings of the tenth ACM international conference on Multimedia
Figure-Ground Separation: A Case Study in Energy Minimization via Evolutionary Computing
EMMCVPR '97 Proceedings of the First International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
The image importance approach to human vision based image quality characterization
Pattern Recognition Letters - Special issue: In memoriam Azriel Rosenfeld
Saliency-guided Enhancement for Volume Visualization
IEEE Transactions on Visualization and Computer Graphics
Eye Tracking Methodology: Theory and Practice
Eye Tracking Methodology: Theory and Practice
Topological Visualization of Brain Diffusion MRI Data
IEEE Transactions on Visualization and Computer Graphics
IEEE Transactions on Multimedia
Detecting false captioning using common-sense reasoning
Digital Investigation: The International Journal of Digital Forensics & Incident Response
Proceedings of the Symposium on Eye Tracking Research and Applications
Hi-index | 0.00 |
Visualized images have always been a preferred method of communication of information contained in complex data sets. However, information contained in the image is not always efficiently communicated to others due to personal differences in the way subjects interpret image content. One of the approaches to solving this issue is to determine high-saliency or eye-catching regions/objects of the image and to share information about the regions of interest (ROI) in the image among researchers. In the present paper, we propose a new method by which an importance map for a visualized image can be constructed. The image is first divided into segments based on a saliency map model, and eye movement data is then acquired and mapped into the segments. The importance score can be calculated by the PageRank algorithm for the network generated by regarding the segments as nodes, and thus an importance map of the image can be constructed. The usefulness of the proposed method is investigated through several experiments.