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...
| Main Authors: | , , , , |
|---|---|
| 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 |