A rotation-invariant corner detector based on the median of subpixelized triangle
Corners are stable local image features that have played a crucial role in various computer vision and image processing tasks. Existing corner detectors generally assume that the distance between every two adjacent pixels is a constant during curvature estimation. However, this assumption is actuall...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-09-01
|
Series: | Journal of King Saud University: Computer and Information Sciences |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823001994 |
_version_ | 1797663901926555648 |
---|---|
author | Xun Sun Baojiang Zhong |
author_facet | Xun Sun Baojiang Zhong |
author_sort | Xun Sun |
collection | DOAJ |
description | Corners are stable local image features that have played a crucial role in various computer vision and image processing tasks. Existing corner detectors generally assume that the distance between every two adjacent pixels is a constant during curvature estimation. However, this assumption is actually invalid, and thus those pixel-based measures of discrete curvature developed and exploited in the existing corner detectors may suffer instability under rotation transformations. To address this fundamental problem, a novel curvature measure is proposed in this paper, which exploits the median of a subpixelized triangle located at the current point to estimate its discrete curvature. It is shown that our proposed curvature measure is invariant under rotation transformations. Based on this novel curvature measure, a new corner detector is further developed. Extensive experimental results show that our proposed corner detector can deliver superior performance over the existing state-of-the-art methods. |
first_indexed | 2024-03-11T19:21:30Z |
format | Article |
id | doaj.art-cd669851542d4af7bdc0cc8bdc3242fb |
institution | Directory Open Access Journal |
issn | 1319-1578 |
language | English |
last_indexed | 2024-03-11T19:21:30Z |
publishDate | 2023-09-01 |
publisher | Elsevier |
record_format | Article |
series | Journal of King Saud University: Computer and Information Sciences |
spelling | doaj.art-cd669851542d4af7bdc0cc8bdc3242fb2023-10-07T04:33:56ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-09-01358101645A rotation-invariant corner detector based on the median of subpixelized triangleXun Sun0Baojiang Zhong1School of Computer Science and Technology, Soochow University, Suzhou 215006, China; School of Computer Engineering, Suzhou Vocational University, Suzhou 215104, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou 215006, China; Corresponding author.Corners are stable local image features that have played a crucial role in various computer vision and image processing tasks. Existing corner detectors generally assume that the distance between every two adjacent pixels is a constant during curvature estimation. However, this assumption is actually invalid, and thus those pixel-based measures of discrete curvature developed and exploited in the existing corner detectors may suffer instability under rotation transformations. To address this fundamental problem, a novel curvature measure is proposed in this paper, which exploits the median of a subpixelized triangle located at the current point to estimate its discrete curvature. It is shown that our proposed curvature measure is invariant under rotation transformations. Based on this novel curvature measure, a new corner detector is further developed. Extensive experimental results show that our proposed corner detector can deliver superior performance over the existing state-of-the-art methods.http://www.sciencedirect.com/science/article/pii/S1319157823001994Corner detectionDiscrete curvatureRotation invariantSubpixelized triangleMedian |
spellingShingle | Xun Sun Baojiang Zhong A rotation-invariant corner detector based on the median of subpixelized triangle Journal of King Saud University: Computer and Information Sciences Corner detection Discrete curvature Rotation invariant Subpixelized triangle Median |
title | A rotation-invariant corner detector based on the median of subpixelized triangle |
title_full | A rotation-invariant corner detector based on the median of subpixelized triangle |
title_fullStr | A rotation-invariant corner detector based on the median of subpixelized triangle |
title_full_unstemmed | A rotation-invariant corner detector based on the median of subpixelized triangle |
title_short | A rotation-invariant corner detector based on the median of subpixelized triangle |
title_sort | rotation invariant corner detector based on the median of subpixelized triangle |
topic | Corner detection Discrete curvature Rotation invariant Subpixelized triangle Median |
url | http://www.sciencedirect.com/science/article/pii/S1319157823001994 |
work_keys_str_mv | AT xunsun arotationinvariantcornerdetectorbasedonthemedianofsubpixelizedtriangle AT baojiangzhong arotationinvariantcornerdetectorbasedonthemedianofsubpixelizedtriangle AT xunsun rotationinvariantcornerdetectorbasedonthemedianofsubpixelizedtriangle AT baojiangzhong rotationinvariantcornerdetectorbasedonthemedianofsubpixelizedtriangle |