Robust Corner Detection Using Local Extrema Differences

Corner detection, crucial for many computer vision tasks due to corner's distinct structural properties, often relies on traditional intensity-based detectors developed before 2000. This paper introduces a novel intensity-based corner detector that surpasses existing methods by solely analyzing...

Full description

Saved in:
Bibliographic Details
Main Authors: Reza Yazdi, Hassan Khotanlou, Hosna Khademfar
Format: Article
Language:English
Published: University of science and culture 2024-01-01
Series:International Journal of Web Research
Subjects:
Online Access:https://ijwr.usc.ac.ir/article_200313_e8e2ef03ef36eb3261087bf4d7811d3f.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846110262972645376
author Reza Yazdi
Hassan Khotanlou
Hosna Khademfar
author_facet Reza Yazdi
Hassan Khotanlou
Hosna Khademfar
author_sort Reza Yazdi
collection DOAJ
description Corner detection, crucial for many computer vision tasks due to corner's distinct structural properties, often relies on traditional intensity-based detectors developed before 2000. This paper introduces a novel intensity-based corner detector that surpasses existing methods by solely analyzing pixel intensity within a 3×3 neighborhood. Our approach leverages a unique corner response function derived from intensity sorting and difference calculations. We conduct a comprehensive evaluation comparing our detector to seven established algorithms using five benchmark images with ground truth corner locations. The evaluation encompasses detection accuracy, localization error under varying noise levels, and repeatability under transformations and degradations. This assessment utilizes 28 diverse images without ground truth data. Experimental results demonstrate the proposed detector's superior overall performance by 3%. It achieves better accuracy in corner localization and reduces both missed detections and false positives. Furthermore, requiring only one parameter for adjustment, it offers computational efficiency and real-time processing potential. Additionally, the generated corner response map holds promise for integration with deep learning architectures, opening possibilities for further exploration.
format Article
id doaj-art-9311cb12e1c846c5ac3be42b10c6b0f3
institution Kabale University
issn 2645-4343
language English
publishDate 2024-01-01
publisher University of science and culture
record_format Article
series International Journal of Web Research
spelling doaj-art-9311cb12e1c846c5ac3be42b10c6b0f32024-12-24T12:02:40ZengUniversity of science and cultureInternational Journal of Web Research2645-43432024-01-0171698410.22133/ijwr.2024.458246.1217Robust Corner Detection Using Local Extrema DifferencesReza Yazdi0Hassan Khotanlou1Hosna Khademfar2RIV Lab, Computer Engineering, Bu-Ali Sina University, Hamadan, IranRIV Lab, Computer Engineering dept., Bu-Ali Sina University, Hamadan, Irandept. of Artificial intelligence, Shargh Golestan higher education institute, Golestan, IranCorner detection, crucial for many computer vision tasks due to corner's distinct structural properties, often relies on traditional intensity-based detectors developed before 2000. This paper introduces a novel intensity-based corner detector that surpasses existing methods by solely analyzing pixel intensity within a 3×3 neighborhood. Our approach leverages a unique corner response function derived from intensity sorting and difference calculations. We conduct a comprehensive evaluation comparing our detector to seven established algorithms using five benchmark images with ground truth corner locations. The evaluation encompasses detection accuracy, localization error under varying noise levels, and repeatability under transformations and degradations. This assessment utilizes 28 diverse images without ground truth data. Experimental results demonstrate the proposed detector's superior overall performance by 3%. It achieves better accuracy in corner localization and reduces both missed detections and false positives. Furthermore, requiring only one parameter for adjustment, it offers computational efficiency and real-time processing potential. Additionally, the generated corner response map holds promise for integration with deep learning architectures, opening possibilities for further exploration.https://ijwr.usc.ac.ir/article_200313_e8e2ef03ef36eb3261087bf4d7811d3f.pdfcorner points detectioncorner detectioninterested pointscorner points
spellingShingle Reza Yazdi
Hassan Khotanlou
Hosna Khademfar
Robust Corner Detection Using Local Extrema Differences
International Journal of Web Research
corner points detection
corner detection
interested points
corner points
title Robust Corner Detection Using Local Extrema Differences
title_full Robust Corner Detection Using Local Extrema Differences
title_fullStr Robust Corner Detection Using Local Extrema Differences
title_full_unstemmed Robust Corner Detection Using Local Extrema Differences
title_short Robust Corner Detection Using Local Extrema Differences
title_sort robust corner detection using local extrema differences
topic corner points detection
corner detection
interested points
corner points
url https://ijwr.usc.ac.ir/article_200313_e8e2ef03ef36eb3261087bf4d7811d3f.pdf
work_keys_str_mv AT rezayazdi robustcornerdetectionusinglocalextremadifferences
AT hassankhotanlou robustcornerdetectionusinglocalextremadifferences
AT hosnakhademfar robustcornerdetectionusinglocalextremadifferences