Cifar-10 Datasets sample images [29].

<div><p>Efficient image retrieval from a variety of datasets is crucial in today's digital world. Visual properties are represented using primitive image signatures in Content Based Image Retrieval (CBIR). Feature vectors are employed to classify images into predefined categories. T...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Aiza Shabir (20896271) (author)
مؤلفون آخرون: Khawaja Tehseen Ahmed (20896274) (author), Arif Mahmood (15871190) (author), Helena Garay (20896277) (author), Luis Eduardo Prado González (20896280) (author), Imran Ashraf (7370771) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852022036068564992
author Aiza Shabir (20896271)
author2 Khawaja Tehseen Ahmed (20896274)
Arif Mahmood (15871190)
Helena Garay (20896277)
Luis Eduardo Prado González (20896280)
Imran Ashraf (7370771)
author2_role author
author
author
author
author
author_facet Aiza Shabir (20896271)
Khawaja Tehseen Ahmed (20896274)
Arif Mahmood (15871190)
Helena Garay (20896277)
Luis Eduardo Prado González (20896280)
Imran Ashraf (7370771)
author_role author
dc.creator.none.fl_str_mv Aiza Shabir (20896271)
Khawaja Tehseen Ahmed (20896274)
Arif Mahmood (15871190)
Helena Garay (20896277)
Luis Eduardo Prado González (20896280)
Imran Ashraf (7370771)
dc.date.none.fl_str_mv 2025-03-18T17:25:30Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0317863.g012
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Cifar-10_Datasets_sample_images_29_/28617473
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biotechnology
Space Science
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
scale space interpolation
locate interest points
define interest points
convolutional neural networks
mean average precision
discriminating &# 160
computing productive sum
combining color features
average retrieval precision
categories including shape
&# 160
predefined categories
including alot
retrieval systems
retrieval system
effective retrieval
tropical fruits
research presents
pixel derivatives
object information
multilevel fusion
information synthesis
feature vectors
extensive experimentation
digital world
corner scores
complicated objects
cnns ).
classify images
cbir ).
dc.title.none.fl_str_mv Cifar-10 Datasets sample images [29].
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>Efficient image retrieval from a variety of datasets is crucial in today's digital world. Visual properties are represented using primitive image signatures in Content Based Image Retrieval (CBIR). Feature vectors are employed to classify images into predefined categories. This research presents a unique feature identification technique based on suppression to locate interest points by computing productive sum of pixel derivatives by computing the differentials for corner scores. Scale space interpolation is applied to define interest points by combining color features from spatially ordered L2 normalized coefficients with shape and object information. Object based feature vectors are formed using high variance coefficients to reduce the complexity and are converted into bag-of-visual-words (BoVW) for effective retrieval and ranking. The presented method encompass feature vectors for information synthesis and improves the discriminating strength of the retrieval system by extracting deep image features including primitive, spatial, and overlayed using multilayer fusion of Convolutional Neural Networks(CNNs). Extensive experimentation is performed on standard image datasets benchmarks, including ALOT, Cifar-10, Corel-10k, Tropical Fruits, and Zubud. These datasets cover wide range of categories including shape, color, texture, spatial, and complicated objects. Experimental results demonstrate considerable improvements in precision and recall rates, average retrieval precision and recall, and mean average precision and recall rates across various image semantic groups within versatile datasets. The integration of traditional feature extraction methods fusion with multilevel CNN advances image sensing and retrieval systems, promising more accurate and efficient image retrieval solutions.</p></div>
eu_rights_str_mv openAccess
id Manara_302eb26cd2e6ba69ffd03466e2934ce3
identifier_str_mv 10.1371/journal.pone.0317863.g012
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28617473
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Cifar-10 Datasets sample images [29].Aiza Shabir (20896271)Khawaja Tehseen Ahmed (20896274)Arif Mahmood (15871190)Helena Garay (20896277)Luis Eduardo Prado González (20896280)Imran Ashraf (7370771)BiotechnologySpace ScienceBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedscale space interpolationlocate interest pointsdefine interest pointsconvolutional neural networksmean average precisiondiscriminating &# 160computing productive sumcombining color featuresaverage retrieval precisioncategories including shape&# 160predefined categoriesincluding alotretrieval systemsretrieval systemeffective retrievaltropical fruitsresearch presentspixel derivativesobject informationmultilevel fusioninformation synthesisfeature vectorsextensive experimentationdigital worldcorner scorescomplicated objectscnns ).classify imagescbir ).<div><p>Efficient image retrieval from a variety of datasets is crucial in today's digital world. Visual properties are represented using primitive image signatures in Content Based Image Retrieval (CBIR). Feature vectors are employed to classify images into predefined categories. This research presents a unique feature identification technique based on suppression to locate interest points by computing productive sum of pixel derivatives by computing the differentials for corner scores. Scale space interpolation is applied to define interest points by combining color features from spatially ordered L2 normalized coefficients with shape and object information. Object based feature vectors are formed using high variance coefficients to reduce the complexity and are converted into bag-of-visual-words (BoVW) for effective retrieval and ranking. The presented method encompass feature vectors for information synthesis and improves the discriminating strength of the retrieval system by extracting deep image features including primitive, spatial, and overlayed using multilayer fusion of Convolutional Neural Networks(CNNs). Extensive experimentation is performed on standard image datasets benchmarks, including ALOT, Cifar-10, Corel-10k, Tropical Fruits, and Zubud. These datasets cover wide range of categories including shape, color, texture, spatial, and complicated objects. Experimental results demonstrate considerable improvements in precision and recall rates, average retrieval precision and recall, and mean average precision and recall rates across various image semantic groups within versatile datasets. The integration of traditional feature extraction methods fusion with multilevel CNN advances image sensing and retrieval systems, promising more accurate and efficient image retrieval solutions.</p></div>2025-03-18T17:25:30ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0317863.g012https://figshare.com/articles/figure/Cifar-10_Datasets_sample_images_29_/28617473CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/286174732025-03-18T17:25:30Z
spellingShingle Cifar-10 Datasets sample images [29].
Aiza Shabir (20896271)
Biotechnology
Space Science
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
scale space interpolation
locate interest points
define interest points
convolutional neural networks
mean average precision
discriminating &# 160
computing productive sum
combining color features
average retrieval precision
categories including shape
&# 160
predefined categories
including alot
retrieval systems
retrieval system
effective retrieval
tropical fruits
research presents
pixel derivatives
object information
multilevel fusion
information synthesis
feature vectors
extensive experimentation
digital world
corner scores
complicated objects
cnns ).
classify images
cbir ).
status_str publishedVersion
title Cifar-10 Datasets sample images [29].
title_full Cifar-10 Datasets sample images [29].
title_fullStr Cifar-10 Datasets sample images [29].
title_full_unstemmed Cifar-10 Datasets sample images [29].
title_short Cifar-10 Datasets sample images [29].
title_sort Cifar-10 Datasets sample images [29].
topic Biotechnology
Space Science
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
scale space interpolation
locate interest points
define interest points
convolutional neural networks
mean average precision
discriminating &# 160
computing productive sum
combining color features
average retrieval precision
categories including shape
&# 160
predefined categories
including alot
retrieval systems
retrieval system
effective retrieval
tropical fruits
research presents
pixel derivatives
object information
multilevel fusion
information synthesis
feature vectors
extensive experimentation
digital world
corner scores
complicated objects
cnns ).
classify images
cbir ).