Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study

• Published in: IEEE transactions on image processing Vol. 22; no. 1; pp. 55 - 69
• Main Authors: Borji, Ali, Sihite, D. N., Itti, L.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.01.2013; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Applied sciences; Area Under Curve; Arrays; Artificial intelligence; Attention - physiology; Bottom-up attention; Computational Biology; Computational modeling; Computer science; control theory; systems; Databases, Factual; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; eye movement prediction; Eye movements; Eye Movements - physiology; Government; Humans; Image processing; Image Processing, Computer-Assisted - methods; Information, signal and communications theory; Mathematical models; model comparison; Models, Statistical; Organizing; Pattern recognition; Pattern recognition. Digital image processing. Computational geometry; Photic Stimulation; Predictive models; Searching; Signal and communications theory; Signal processing; Signal, noise; State of the art; Studies; Telecommunications and information theory; Videos; Vision systems; Visual; visual attention; visual saliency; Visualization; Computer vision; State of the art; Target tracking; model comparison; Artificial vision; Vision system; Pattern recognition; Object recognition; Computational complexity; Modeling; Eye movement; Robotics; Accuracy; eye movement prediction; Bottom-up attention; Quality control; Object detection; Open market; Visual saliency; Visual attention; Target detection; Comparative study; Quantitative analysis; Image evaluation

Visual attention is a process that enables biological and machine vision systems to select the most relevant regions from a scene. Relevance is determined by two components: 1) top-down factors driven by task and 2) bottom-up factors that highlight image regions that are different from their surroun...