Bienvenido al Repositorio Institucional del Concytec

El Repositorio Institucional del Concytec tiene como objetivo permitir el libre acceso a la producción científica institucional, optimizando su visibilidad; así mismo garantizar la preservación y conservación de la información relacionada a la ciencia, tecnología e innovación.



Display.item.jsp


Por favor, utiliza este identificador para citar o enlazar este ítem:
http://hdl.handle.net/20.500.12390/2804


Título: Evaluating Deep Convolutional Neural Networks as Texture Feature Extractors
Autor(es): Scabini, Leonardo F. S. 
Condori, Rayner H. M. 
Ribas, Lucas C. 
Bruno, Odemir M. 
Resumen: Texture is an important visual property which has been largely employed for image characterization. Recently, Convolutional Networks has been the predominant approach on Computer Vision, and their application on texture analysis shows interesting results. However, their popularity steers around object recognition, and several convolutional architectures have been proposed and trained for this task. Therefore, this works evaluates 17 of the most diffused Deep Convolutional Neural Networks when employed for texture analysis as feature extractors. Image descriptors are obtained through Global Average Pooling over the output of the last convolutional layer of networks with random weights or learned from the ImageNet dataset. The analysis is performed under 6 texture datasets and using 3 different supervised classifiers (KNN, LDA, and SVM). Results using networks with random weights indicates that the architecture alone plays an important role in texture characterization, and it can even provide useful features for classification for some datasets. On the other hand, we found that although ImageNet weights usually provide the best results it can also perform similar to random weights in some cases, indicating that transferring convolutional weights learned on ImageNet may not always be appropriate for texture analysis. When comparing the best models, our results corroborate that DenseNet presents the highest overall performance while keeping a significantly small number of hyperparameters, thus we recommend its use for texture characterization.
Tema: Deep Convolutional;Neural Network;Texture analysis;Feature extraction
Editorial: Springer International Publishing
Fecha de publicación: 2019
Publicado en: IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT II 
Financiamiento: 009-2018-FONDECYT 
Tipo de publicación: info:eu-repo/semantics/article
Identificador Handle: http://hdl.handle.net/20.500.12390/2804
DOI: 10.1007/978-3-030-30645-8_18
Nivel de acceso: info:eu-repo/semantics/closedAccess
Colección:4.1 Organización de eventos

Registro Dublin Core completo



Páginas vistas

2
marcado en 20-oct-2021

Google ScholarTM

Check

Altmetric

  • Compartir este item
  • QR Code

Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.