Unsupervised Regions of Interest Extraction based on Visual Attention and SIFT
B. Chaudhury, Oge Marques, Gustavo Benvenutti Borba, Humberto Remigio Gamba · 2010
This paper presents an unsupervised approach to ROI extraction, using a combination of salient keypoints fromScale Invariant Feature Descriptors (SIFT) and points ofattention (POAs) from a computational model of human visual attention (VA).