首頁Home › 視覺認知與心理學 Visual Perception & Psychology
視覺顯著性
1這是什麼What is it?
視覺顯著性是畫面中某區域因與周圍在亮度、色彩、方向等特徵上差異而吸引注意的程度,Itti 與 Koch(1998)建立了經典的計算顯著性模型。顯著圖可預測初步注視分布,但無法完全涵蓋任務與語意因素;深度學習模型提升了預測準確度。
Visual saliency is the degree to which an area attracts attention by differing from its surroundings in features such as luminance, color and orientation, with Itti and Koch (1998) building a classic computational saliency model. Saliency maps can predict initial fixation distribution but cannot fully capture task and semantic factors, and deep-learning models have improved prediction accuracy.
2常被用在哪種研究問題Typical research questions
常見問法:顯著性模型能否預測注視位置?
視覺顯著性預測注意會落在何處。本研究以顯著性模型預測與實際眼動資料比較,檢驗其對設計稿的預測力。
Visual saliency predicts where attention falls. This study compares saliency model predictions with actual eye-movement data to test predictive power for design drafts.
撰寫內容,非真實研究結果,請與指導教授討論後改寫。
Written as a model example, not a real finding. Please revise with your advisor.
3怎麼測它How to measure it
顯著圖計算+眼動資料比對
Measurement notes are written in Chinese. Switch to 中/EN to read them.
4代表文獻Key references
英文論文(2000 年後)English paper (post-2000)
Itti, L., & Koch, C. (2001). Computational modelling of visual attention. Nature Reviews Neuroscience, 2(3).
中文論文(2000 年後)
中文論文為預填檢索連結,請自行挑選一篇 2000 年後的期刊論文並核對作者、年份、出處後再引用。
英文引用來自模型整理,引用前請務必核對並閱讀原文。English citations are compiled by a model. Verify and read the original before citing.