Image Local Features Description Through Polynomial Approximation

<p dir="ltr">This work introduces a novel local patch descriptor that remains invariant under varying conditions of orientation, viewpoint, scale, and illumination. The proposed descriptor incorporate polynomials of various degrees to approximate the local patch within the image. Bef...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Fawad - (17018015) (author)
مؤلفون آخرون: Muhibur Rahman (16864351) (author), Muhammad Jamil Khan (16864352) (author), Muhammad Adeel Asghar (16864353) (author), Yasar Amin (16864354) (author), Salman Badnava (16864356) (author), Seyed Sajad Mirjavadi (16864357) (author)
منشور في: 2019
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513561178406912
author Fawad - (17018015)
author2 Muhibur Rahman (16864351)
Muhammad Jamil Khan (16864352)
Muhammad Adeel Asghar (16864353)
Yasar Amin (16864354)
Salman Badnava (16864356)
Seyed Sajad Mirjavadi (16864357)
author2_role author
author
author
author
author
author
author_facet Fawad - (17018015)
Muhibur Rahman (16864351)
Muhammad Jamil Khan (16864352)
Muhammad Adeel Asghar (16864353)
Yasar Amin (16864354)
Salman Badnava (16864356)
Seyed Sajad Mirjavadi (16864357)
author_role author
dc.creator.none.fl_str_mv Fawad - (17018015)
Muhibur Rahman (16864351)
Muhammad Jamil Khan (16864352)
Muhammad Adeel Asghar (16864353)
Yasar Amin (16864354)
Salman Badnava (16864356)
Seyed Sajad Mirjavadi (16864357)
dc.date.none.fl_str_mv 2019-12-13T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/ACCESS.2019.2959326
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Image_Local_Features_Description_Through_Polynomial_Approximation/24006804
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Applied computing
Computer vision and multimedia computation
Feature extraction
Lighting
Histograms
Image edge detection
Detectors
Shape
Image coding
Covariant
Descriptor
Handcrafted feature
Patch
Textures
dc.title.none.fl_str_mv Image Local Features Description Through Polynomial Approximation
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">This work introduces a novel local patch descriptor that remains invariant under varying conditions of orientation, viewpoint, scale, and illumination. The proposed descriptor incorporate polynomials of various degrees to approximate the local patch within the image. Before feature detection and approximation, the image micro-texture is eliminated through a guided image filter with the potential to preserve the edges of the objects. The rotation invariance is achieved by aligning the local patch around the Harris corner through the dominant orientation shift algorithm. Weighted threshold histogram equalization (WTHE) is employed to make the descriptor in-sensitive to illumination changes. The correlation coefficient is used instead of Euclidean distance to improve the matching accuracy. The proposed descriptor has been extensively evaluated on the Oxford’s affine covariant regions dataset, and absolute and transition tilt dataset. The experimental results show that our proposed descriptor can categorize the feature with more distinctiveness in comparison to state-of-the-art descriptors.</p><h2>Other Information</h2><p dir="ltr">Published in: Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1109/access.2019.2959326" rel="noreferrer" target="_blank"><u>http://dx.doi.org/10.1109/access.2019.2959326</u></a></p>
eu_rights_str_mv openAccess
id Manara2_97ab5b4bbcd227bd89aac6d86b5e97c0
identifier_str_mv 10.1109/ACCESS.2019.2959326
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24006804
publishDate 2019
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Image Local Features Description Through Polynomial ApproximationFawad - (17018015)Muhibur Rahman (16864351)Muhammad Jamil Khan (16864352)Muhammad Adeel Asghar (16864353)Yasar Amin (16864354)Salman Badnava (16864356)Seyed Sajad Mirjavadi (16864357)Information and computing sciencesApplied computingComputer vision and multimedia computationFeature extractionLightingHistogramsImage edge detectionDetectorsShapeImage codingCovariantDescriptorHandcrafted featurePatchTextures<p dir="ltr">This work introduces a novel local patch descriptor that remains invariant under varying conditions of orientation, viewpoint, scale, and illumination. The proposed descriptor incorporate polynomials of various degrees to approximate the local patch within the image. Before feature detection and approximation, the image micro-texture is eliminated through a guided image filter with the potential to preserve the edges of the objects. The rotation invariance is achieved by aligning the local patch around the Harris corner through the dominant orientation shift algorithm. Weighted threshold histogram equalization (WTHE) is employed to make the descriptor in-sensitive to illumination changes. The correlation coefficient is used instead of Euclidean distance to improve the matching accuracy. The proposed descriptor has been extensively evaluated on the Oxford’s affine covariant regions dataset, and absolute and transition tilt dataset. The experimental results show that our proposed descriptor can categorize the feature with more distinctiveness in comparison to state-of-the-art descriptors.</p><h2>Other Information</h2><p dir="ltr">Published in: Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1109/access.2019.2959326" rel="noreferrer" target="_blank"><u>http://dx.doi.org/10.1109/access.2019.2959326</u></a></p>2019-12-13T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/ACCESS.2019.2959326https://figshare.com/articles/journal_contribution/Image_Local_Features_Description_Through_Polynomial_Approximation/24006804CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240068042019-12-13T00:00:00Z
spellingShingle Image Local Features Description Through Polynomial Approximation
Fawad - (17018015)
Information and computing sciences
Applied computing
Computer vision and multimedia computation
Feature extraction
Lighting
Histograms
Image edge detection
Detectors
Shape
Image coding
Covariant
Descriptor
Handcrafted feature
Patch
Textures
status_str publishedVersion
title Image Local Features Description Through Polynomial Approximation
title_full Image Local Features Description Through Polynomial Approximation
title_fullStr Image Local Features Description Through Polynomial Approximation
title_full_unstemmed Image Local Features Description Through Polynomial Approximation
title_short Image Local Features Description Through Polynomial Approximation
title_sort Image Local Features Description Through Polynomial Approximation
topic Information and computing sciences
Applied computing
Computer vision and multimedia computation
Feature extraction
Lighting
Histograms
Image edge detection
Detectors
Shape
Image coding
Covariant
Descriptor
Handcrafted feature
Patch
Textures