Open AccessPoisson‐distribution‐based approach for salient region detection
Author(s) -
Manke R.,
Jalal A.S.
Publication year - 2015
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2014.3334
Subject(s) - salient , clutter , artificial intelligence , computer science , focus (optics) , computer vision , process (computing) , object detection , filter (signal processing) , image (mathematics) , discriminator , field (mathematics) , false alarm , pattern recognition (psychology) , mathematics , telecommunications , radar , physics , detector , pure mathematics , optics , operating system
Attention is given to the behavioural and cognitive process of selectively concentrating on one object in an image while ignoring the others. Attention‐grabbing parts of the visual field are inspected with great keenness. Owing to the limited capacity of the visual system, the retina cannot process everything that falls on it. Instead, the brain relies on attention to bring salient details into focus and filter out background clutter. Salient region detection deals with finding those regions in an image that gain the viewer's attention most. An approach is proposed for salient region detection using the Poisson distribution. The proposed approach does not require any prior training and has been evaluated on the MSRA dataset. The performance is consistent in terms of recall, precision and execution time.