Human attention plays an important role in human visual system. We assume that the Gestalt law is one of the important factors to guide human selective attention. We conducted series of studies in which we hypothesised that regions of image that get more attention in an object recognition task, confirm to one or more gestalt principles and subconsciously attract human attention which eventually help in object recognition. In our study, we collected attention parts of images by analysing eye movement of participants. Then we compared Gestalt scores of high attention parts with those of non-attended random parts. The results suggested that continuity and symmetry of features attract human attention.

​

We proposed a computational model to extend the region of attention in a visual scene. We assumed that the visual information that is collected through bottom-up process is integrated by various mechanisms of perception process, which in result further decides the attention regions of the object to accurately determine the object. This cycle is known as perception-action cycle. In this study we tried to quantify relation between initial attention region and surrounding regions using Gestalt principles

​

​

​

​

​

​

​

​

​

​

​

​

​