Abstract
Currently, there are many algorithms for evaluating video quality, which use the region of interest search algorithm for correct operation. In order for algorithm developers to improve the performance of region-of-interest search methods, in this paper we compare algorithms for searching regions of interest using data obtained during subjective tests. Subjective estimates of the region of video interest require a lot of time for experimentation and are not feasible in real-time applications. Interest in this technology is growing every year. In this article, we compare several algorithms for calculating regions of interest: a neural network, an algorithm for calculating a binarization threshold for a grayscale image, a method for detecting a prominent area using a high-dimensional color transformation, and a watershed segmentation algorithm. This work will be useful for video compression researchers, as well as for creating additional test materials, planning future experiments and improving existing algorithms for searching regions of interest.
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.
