Msc. thesis
Visual Attention Models
Supervisor: RNDr. Elena Šikudová, PhD.





Visual attention is very important in human visual perception. It is the ability of a vision system to detect salient objects of an observed scene. This scientic discipline has been studied for over a century. Nowadays, it is involved in the disciplines of psychophysics, cognitive neuroscience and computer science.
This master thesis describes several visual attention models for detecting salient objects in complex scene and focuses on model based on local context suppression of multiple cues presented by Hu. Although this model is useful to capture visual attention in images containing small objects, it fails in detecting faces as salient objects. Therefore, we improved the model by adding additional attention cue. We propose a system for detecting salient objects based on texture, where face detection is used as an additional attention cue.


Keywords: Visual Attention, Texture attention cue, Salient object, Face detection