Classification of corals in reflectance and fluorescence images using convolutional neural network representations

© 2018 IEEE. Coral species, with complex morphology and ambiguous boundaries, pose a great challenge for automated classification. CNN activations, which are extracted from fully connected layers of deep networks (FC features), have been successfully used as powerful universal representations in man...

Full description

Bibliographic Details
Main Authors: Xu, L., Bennamoun, M., An, Senjian, Sohel, F., Boussaid, F.
Format: Conference Paper
Published: 2018
Online Access:http://hdl.handle.net/20.500.11937/71733
_version_ 1848762558224269312
author Xu, L.
Bennamoun, M.
An, Senjian
Sohel, F.
Boussaid, F.
author_facet Xu, L.
Bennamoun, M.
An, Senjian
Sohel, F.
Boussaid, F.
author_sort Xu, L.
building Curtin Institutional Repository
collection Online Access
description © 2018 IEEE. Coral species, with complex morphology and ambiguous boundaries, pose a great challenge for automated classification. CNN activations, which are extracted from fully connected layers of deep networks (FC features), have been successfully used as powerful universal representations in many visual tasks. In this paper, we investigate the transferability and combined performance of FC features and CONY features (extracted from convolutional layers) in the coral classification of two image modalities (reflectance and fluorescence), using a typical deep network (e.g. VGGNet). We exploit vector of locally aggregated descriptors (VLAD) encoding and principal component analysis (PCA) to compress dense CONY features into a compact representation. Experimental results demonstrate that encoded CONV3 features achieve superior performances on reflectance and fluorescence coral images, compared to FC features. The combination of these two features further improves the overall accuracy and achieves state-of-the-art performance on the challenging EFC dataset.
first_indexed 2025-11-14T10:49:28Z
format Conference Paper
id curtin-20.500.11937-71733
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:49:28Z
publishDate 2018
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-717332018-12-13T09:31:54Z Classification of corals in reflectance and fluorescence images using convolutional neural network representations Xu, L. Bennamoun, M. An, Senjian Sohel, F. Boussaid, F. © 2018 IEEE. Coral species, with complex morphology and ambiguous boundaries, pose a great challenge for automated classification. CNN activations, which are extracted from fully connected layers of deep networks (FC features), have been successfully used as powerful universal representations in many visual tasks. In this paper, we investigate the transferability and combined performance of FC features and CONY features (extracted from convolutional layers) in the coral classification of two image modalities (reflectance and fluorescence), using a typical deep network (e.g. VGGNet). We exploit vector of locally aggregated descriptors (VLAD) encoding and principal component analysis (PCA) to compress dense CONY features into a compact representation. Experimental results demonstrate that encoded CONV3 features achieve superior performances on reflectance and fluorescence coral images, compared to FC features. The combination of these two features further improves the overall accuracy and achieves state-of-the-art performance on the challenging EFC dataset. 2018 Conference Paper http://hdl.handle.net/20.500.11937/71733 10.1109/ICASSP.2018.8462574 restricted
spellingShingle Xu, L.
Bennamoun, M.
An, Senjian
Sohel, F.
Boussaid, F.
Classification of corals in reflectance and fluorescence images using convolutional neural network representations
title Classification of corals in reflectance and fluorescence images using convolutional neural network representations
title_full Classification of corals in reflectance and fluorescence images using convolutional neural network representations
title_fullStr Classification of corals in reflectance and fluorescence images using convolutional neural network representations
title_full_unstemmed Classification of corals in reflectance and fluorescence images using convolutional neural network representations
title_short Classification of corals in reflectance and fluorescence images using convolutional neural network representations
title_sort classification of corals in reflectance and fluorescence images using convolutional neural network representations
url http://hdl.handle.net/20.500.11937/71733