Title :
Spatial bayesian surprise for image saliency and quality assessment
Author :
Gkioulekas, Ioannis ; Evangelopoulos, Georgios ; Maragos, Petros
Author_Institution :
Harvard SEAS, Cambridge, MA, USA
Abstract :
We propose an alternative interpretation of Bayesian surprise in the spatial domain, to account for saliency arising from contrast in image context. Our saliency formulation is integrated in three different application scenaria, with considerable improvements in performance: 1) visual attention prediction, validated using eye- and mouse-tracking data, 2) region of interest detection, to improve scale selection and localization, 3) image quality assessment to achieve better agreement with subjective human evaluations.
Keywords :
Bayes methods; image processing; object detection; image quality assessment; image saliency; region-of-interest detection; spatial Bayesian surprise; visual attention prediction; Bayesian methods; Context; Detectors; Entropy; Image quality; Measurement; Visualization; Bayesian surprise; Image saliency; image quality assessment; region detection; visual attention;
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2010.5650991
