Localization of image fragments with high frequency intensity oscillation
-
Published:2023-08-15
Issue:2
Volume:6
Page:597
-
ISSN:2630-5046
-
Container-title:Journal of Autonomous Intelligence
-
language:
-
Short-container-title:J Autonom Intell
Author:
Trubitsyn Andrey,Shadrin Maksim,Serezhin Andrey
Abstract
<p>The problem of detecting image fragments characterized by high-frequency fluctuations in spatial intensity in the general case has not been previously considered in the literature. The article researches a sequence of known and new algorithms that allows detection and localization of such fragments. The geometric localization of the fragments is based on the Hough transform of the pixel array of the external contours of the connected components. The components connecting becomes possible due to the use of the oscillation function proposed by the authors. The oscillation function turns out to be an effective tool for highlighting intensity fluctuations zones in an image and is superior in reliability to alternative methods for detecting such zones, based, for example, on gradient methods. The article demonstrates examples of localization of the image fragments with different levels of background complexity.</p>
Publisher
Frontier Scientific Publishing Pte Ltd
Subject
Artificial Intelligence,Computer Science Applications,Human-Computer Interaction,Computer Science (miscellaneous)
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Detection, localization and Transformation of twoDimensional Graphic Code;Proceedings of the 33rd International Conference on Computer Graphics and Vision;2023