Abstract
Visual saliency is the distinct perceptual quality which makes some subsets in an image stand out from their neighbours and immediately grab human attention in the early vision. Visual saliency is useful in locating the region of interest. Quick visual saliency detection is desirable in an application that uses the region of interest. The paper embeds a new heuristic module in the original hypercomplex Fourier transform based model. It allows generating saliency maps falling in the search path only, and hence reduces the number of intermediate saliency maps from N to average value $$log_2 N+1$$ . Ultimately, speed up the original saliency model significantly.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
