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...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , |
| 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 ). |