出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The determination of Region-of-Interest has been recognised as an important means by whichunimportant image content can be identified and excluded during image compression or imagemodelling, however existing Region-of-Interest detection methods are computationallyexpensive thus are mostly unsuitable for managing large number of images and the compressionof images especially for real-time video applications. This paper therefore proposes anunsupervised algorithm that takes advantage of the high computation speed being offered bySpeeded-Up Robust Features (SURF) and Features from Accelerated Segment Test (FAST) toachieve fast and efficient Region-of-Interest detection.
