作者: Zhen Liang , Hong Fu , Zheru Chi , Dagan Feng
DOI: 10.1109/ICIP.2010.5651804
关键词: Image segmentation 、 Video tracking 、 Visualization 、 Computer vision 、 Human visual system model 、 Eye tracking 、 Artificial intelligence 、 Weighting 、 Computer science 、 Visual attention 、 Salience (neuroscience)
摘要: Computational visual attention modeling is a topic of increasing importance in machine understanding images. In this paper, we present an approach to refine region based model with eye tracking data. This paper has three main contributions. (1) A concept fixation mask proposed describe the saliency image by weighting segmented regions using measures obtained Human Visual System (HVS) or computational models. (2) Genetic Algorithm (GA) scheme for refining proposed. (3) An evaluation method developed measure correlation between result from and that HVS terms mask.