The determination of Region-of-Interest has been re cognised as an important means by which unimportant image content can be identified and exc luded during image compression or image modelling, however existing Region-of-Interest dete ction methods are computationally expensive thus are mostly unsuitable for managing l arge number of images and the compression of images especially for real-time video applicatio ns. This paper therefore proposes an unsupervised algorithm that takes advantage of the high computation speed being offered by Speeded-Up Robust Features (SURF) and Features from Accelerated Segment Test (FAST) to achieve fast and efficient Region-of-Interest detec tion.
A. A. Olaode, G. Naghdy & C. A. Todd, "Unsupervised region of intrest detection using fast and surf," Computer Science & Information Technology, vol. 5, (4) pp. 63-72, 2015.