Classification of corals in reflectance and fluorescence images using convolutional neural network representations
dc.contributor.author | Xu, L. | |
dc.contributor.author | Bennamoun, M. | |
dc.contributor.author | An, Senjian | |
dc.contributor.author | Sohel, F. | |
dc.contributor.author | Boussaid, F. | |
dc.date.accessioned | 2018-12-13T09:11:07Z | |
dc.date.available | 2018-12-13T09:11:07Z | |
dc.date.created | 2018-12-12T02:46:24Z | |
dc.date.issued | 2018 | |
dc.identifier.citation | Xu, L. and Bennamoun, M. and An, S. and Sohel, F. and Boussaid, F. 2018. Classification of corals in reflectance and fluorescence images using convolutional neural network representations, pp. 1493-1497. | |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/71733 | |
dc.identifier.doi | 10.1109/ICASSP.2018.8462574 | |
dc.description.abstract |
© 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. | |
dc.title | Classification of corals in reflectance and fluorescence images using convolutional neural network representations | |
dc.type | Conference Paper | |
dcterms.source.volume | 2018-April | |
dcterms.source.startPage | 1493 | |
dcterms.source.endPage | 1497 | |
dcterms.source.title | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | |
dcterms.source.series | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | |
dcterms.source.isbn | 9781538646588 | |
curtin.department | School of Electrical Engineering, Computing and Mathematical Science (EECMS) | |
curtin.accessStatus | Fulltext not available |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |