Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet

This study evaluates the use of feature extraction with a pre-trained ResNet50 model for similarity search tasks. We employed transfer learning from both initial and intermediate layers of ResNet50 and applied a robust preprocessing approach, including resizing and Gaussian blur, to optimize feature...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pascal, Andrés, Planas, Adrián, Vidal, Zoe Florencia, Bonti, Agustina, Tonelotto, Lucas, Castiglioni, León
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2024
Materias:	Ciencias Informáticas Image Similarity Search Feature Extraction CNNs Transfer Learning Logos Paintings
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/176283
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-176283
record_format	dspace
spelling	I19-R120-10915-1762832025-02-07T20:05:00Z http://sedici.unlp.edu.ar/handle/10915/176283 Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet Pascal, Andrés Planas, Adrián Vidal, Zoe Florencia Bonti, Agustina Tonelotto, Lucas Castiglioni, León 2024-10 2024 2025-02-07T17:02:52Z en Ciencias Informáticas Image Similarity Search Feature Extraction CNNs Transfer Learning Logos Paintings This study evaluates the use of feature extraction with a pre-trained ResNet50 model for similarity search tasks. We employed transfer learning from both initial and intermediate layers of ResNet50 and applied a robust preprocessing approach, including resizing and Gaussian blur, to optimize feature extraction. The method achieved over 90% accuracy in nearest neighbor (NN) and k-Nearest Neighbors (k=3 and k=5) searches for both logos and paintings datasets. Notably, our approach does not require fine-tuning, which is advantageous when only one instance of each element is available. Overall, the method is effective and practical for similarity search applications. Red de Universidades con Carreras en Informática Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 82-93
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Image Similarity Search Feature Extraction CNNs Transfer Learning Logos Paintings
spellingShingle	Ciencias Informáticas Image Similarity Search Feature Extraction CNNs Transfer Learning Logos Paintings Pascal, Andrés Planas, Adrián Vidal, Zoe Florencia Bonti, Agustina Tonelotto, Lucas Castiglioni, León Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet
topic_facet	Ciencias Informáticas Image Similarity Search Feature Extraction CNNs Transfer Learning Logos Paintings
description	This study evaluates the use of feature extraction with a pre-trained ResNet50 model for similarity search tasks. We employed transfer learning from both initial and intermediate layers of ResNet50 and applied a robust preprocessing approach, including resizing and Gaussian blur, to optimize feature extraction. The method achieved over 90% accuracy in nearest neighbor (NN) and k-Nearest Neighbors (k=3 and k=5) searches for both logos and paintings datasets. Notably, our approach does not require fine-tuning, which is advantageous when only one instance of each element is available. Overall, the method is effective and practical for similarity search applications.
format	Objeto de conferencia Objeto de conferencia
author	Pascal, Andrés Planas, Adrián Vidal, Zoe Florencia Bonti, Agustina Tonelotto, Lucas Castiglioni, León
author_facet	Pascal, Andrés Planas, Adrián Vidal, Zoe Florencia Bonti, Agustina Tonelotto, Lucas Castiglioni, León
author_sort	Pascal, Andrés
title	Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet
title_short	Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet
title_full	Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet
title_fullStr	Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet
title_full_unstemmed	Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet
title_sort	image feature extraction for similarity searching using transfer learning with resnet
publishDate	2024
url	http://sedici.unlp.edu.ar/handle/10915/176283
work_keys_str_mv	AT pascalandres imagefeatureextractionforsimilaritysearchingusingtransferlearningwithresnet AT planasadrian imagefeatureextractionforsimilaritysearchingusingtransferlearningwithresnet AT vidalzoeflorencia imagefeatureextractionforsimilaritysearchingusingtransferlearningwithresnet AT bontiagustina imagefeatureextractionforsimilaritysearchingusingtransferlearningwithresnet AT tonelottolucas imagefeatureextractionforsimilaritysearchingusingtransferlearningwithresnet AT castiglionileon imagefeatureextractionforsimilaritysearchingusingtransferlearningwithresnet
_version_	1845116778022174720

Image Feature Extraction for Similarity Searching Using Transfer Learning with ResNet

Ejemplares similares