Classification of melanoma images with fisher vectors and deep learning
The present work corresponds to the application of techniques of data mining and deep training of neural networks (deep learning) with the objective of classifying images of moles in ‘Melanomas’ or ‘No Melanomas’. For this purpose an ensemble of three classifiers will be created. The first correspon...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | SER |
Materias: | |
Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_03029743_v11401LNCS_n_p732_Liberman |
Aporte de: |
id |
todo:paper_03029743_v11401LNCS_n_p732_Liberman |
---|---|
record_format |
dspace |
spelling |
todo:paper_03029743_v11401LNCS_n_p732_Liberman2023-10-03T15:18:49Z Classification of melanoma images with fisher vectors and deep learning Liberman, G. Acevedo, D. Mejail, M. Vera-Rodriguez R. Fierrez J. Morales A. Deep learning Fisher vectors Melanoma classification Convolution Data mining Dermatology Image classification Oncology Support vector machines Vectors Convolutional networks Descriptors Fisher vectors Hybrid model Net networks Segmented images Deep learning The present work corresponds to the application of techniques of data mining and deep training of neural networks (deep learning) with the objective of classifying images of moles in ‘Melanomas’ or ‘No Melanomas’. For this purpose an ensemble of three classifiers will be created. The first corresponds to a convolutional network VGG-16, the other two correspond to two hybrid models. Each hybrid model is composed of a VGG-16 input network and a Support Vector Machine (SVM) as a classifier. These models will be trained with Fisher Vectors (FVs) calculated with the descriptors that are the output of the convolutional network aforementioned. The difference between these two last classifiers lies in the fact that one has segmented images as input of the VGG-16 network, while the other uses non-segmented images. Segmentation is done by means of an U-NET network. Finally, we will analyze the performance of the hybrid models: The VGG-16 network and the ensemble that incorporates the three classifiers. © Springer Nature Switzerland AG 2019. SER info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_03029743_v11401LNCS_n_p732_Liberman |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
Deep learning Fisher vectors Melanoma classification Convolution Data mining Dermatology Image classification Oncology Support vector machines Vectors Convolutional networks Descriptors Fisher vectors Hybrid model Net networks Segmented images Deep learning |
spellingShingle |
Deep learning Fisher vectors Melanoma classification Convolution Data mining Dermatology Image classification Oncology Support vector machines Vectors Convolutional networks Descriptors Fisher vectors Hybrid model Net networks Segmented images Deep learning Liberman, G. Acevedo, D. Mejail, M. Vera-Rodriguez R. Fierrez J. Morales A. Classification of melanoma images with fisher vectors and deep learning |
topic_facet |
Deep learning Fisher vectors Melanoma classification Convolution Data mining Dermatology Image classification Oncology Support vector machines Vectors Convolutional networks Descriptors Fisher vectors Hybrid model Net networks Segmented images Deep learning |
description |
The present work corresponds to the application of techniques of data mining and deep training of neural networks (deep learning) with the objective of classifying images of moles in ‘Melanomas’ or ‘No Melanomas’. For this purpose an ensemble of three classifiers will be created. The first corresponds to a convolutional network VGG-16, the other two correspond to two hybrid models. Each hybrid model is composed of a VGG-16 input network and a Support Vector Machine (SVM) as a classifier. These models will be trained with Fisher Vectors (FVs) calculated with the descriptors that are the output of the convolutional network aforementioned. The difference between these two last classifiers lies in the fact that one has segmented images as input of the VGG-16 network, while the other uses non-segmented images. Segmentation is done by means of an U-NET network. Finally, we will analyze the performance of the hybrid models: The VGG-16 network and the ensemble that incorporates the three classifiers. © Springer Nature Switzerland AG 2019. |
format |
SER |
author |
Liberman, G. Acevedo, D. Mejail, M. Vera-Rodriguez R. Fierrez J. Morales A. |
author_facet |
Liberman, G. Acevedo, D. Mejail, M. Vera-Rodriguez R. Fierrez J. Morales A. |
author_sort |
Liberman, G. |
title |
Classification of melanoma images with fisher vectors and deep learning |
title_short |
Classification of melanoma images with fisher vectors and deep learning |
title_full |
Classification of melanoma images with fisher vectors and deep learning |
title_fullStr |
Classification of melanoma images with fisher vectors and deep learning |
title_full_unstemmed |
Classification of melanoma images with fisher vectors and deep learning |
title_sort |
classification of melanoma images with fisher vectors and deep learning |
url |
http://hdl.handle.net/20.500.12110/paper_03029743_v11401LNCS_n_p732_Liberman |
work_keys_str_mv |
AT libermang classificationofmelanomaimageswithfishervectorsanddeeplearning AT acevedod classificationofmelanomaimageswithfishervectorsanddeeplearning AT mejailm classificationofmelanomaimageswithfishervectorsanddeeplearning AT verarodriguezr classificationofmelanomaimageswithfishervectorsanddeeplearning AT fierrezj classificationofmelanomaimageswithfishervectorsanddeeplearning AT moralesa classificationofmelanomaimageswithfishervectorsanddeeplearning |
_version_ |
1782026400416399360 |