Rudra Sawant
Gianluca Demartini
ABSTRACT
Several approaches have been taken by different scientists over the years to create taxonomy of coral species by looking at their morphology. On molecular examination, the taxonomies created have revealed to have incorrect classifications. In this project we aim to find a relationship between different types of corals and classify them by using image classification and clustering techniques on a coral dataset provided by Queensland Museum (QM), Australia. We use the VGG16 [9], InceptionV3 [10] and DenseNet [5] models which are pretrained on the ImageNet dataset, to train and extract feature embeddings from the coral images in the QM dataset. These embeddings are then clustered using the Agglomerative Hierarchical Clustering to obtain a general hierarchy of corals. We show that DenseNet performs the best among the three models on the image classification task and can be used to extract the feature embeddings. Using Agglomerative Hierarchical Clustering with average link criterion on these embeddings, we can generate a general hierarchy of corals.
Supplemental Material
Available for Download
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. 248–255. https://doi.org/10.1109/CVPR.2009.5206848Google Scholar
Cross Ref
- Bo Dong and Xinnian Wang. 2018. A transfer learning based feature-weak-relevant method for image clustering. arXiv (2018).Google Scholar
- Anabel Gómez-Ríos, Siham Tabik, Julián Luengo, A. S.M. Shihavuddin, and Francisco Herrera. 2019. Coral species identification with texture or structure images using a two-level classifier based on Convolutional Neural Networks. Knowledge-Based Systems 184 (2019), 104891. https://doi.org/10.1016/j.knosys.2019.104891Google ScholarCross Ref
- Anabel Gómez-Ríos, Siham Tabik, Julián Luengo, A. S.M. Shihavuddin, Bartosz Krawczyk, and Francisco Herrera. 2019. Towards highly accurate coral texture images classification using deep convolutional neural networks and data augmentation. Expert Systems with Applications 118 (2019), 315–328. https://doi.org/10.1016/j.eswa.2018.10.010Google ScholarDigital Library
- Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2016. Densely Connected Convolutional Networks. (8 2016). http://arxiv.org/abs/1608.06993Google Scholar
- A Mahmood, M Bennamoun, S An, F Sohel, F Boussaid, R Hovey, G Kendrick, and R B Fisher. 2016. Coral Classification with Hybrid Feature Representations. Ieee (2016), 4673–9961. Issue 978.Google Scholar
- Md Modasshir, Alberto Quattrini Li, and Ioannis Rekleitis. 2019. MDNet: Multi-Patch Dense Network for Coral Classification. OCEANS 2018 MTS/IEEE Charleston, OCEAN 2018(2019), 1–6. https://doi.org/10.1109/OCEANS.2018.8604478Google Scholar
- John Pavlus. 2016. Computers Now Recognize Patterns Better Than Humans Can. https://www.scientificamerican.com/article/computers-now-recognize-patterns-better-than-humans-can/Google Scholar
- Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. (9 2014). http://arxiv.org/abs/1409.1556Google Scholar
- Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. (12 2015). http://arxiv.org/abs/1512.00567Google Scholar
- John Veron. 2013. Overview of the taxonomy of zooxanthellate Scleractinia. Zoological Journal of the Linnean Society 169 (2013), 485–508. Issue 3. https://doi.org/10.1111/zoj.12076Google ScholarCross Ref
- Wenbo Zhu, Birgit Braun, Leo H. Chiang, and Jose A. Romagnoli. 2021. Investigation of Transfer Learning for Image Classification and Impact on Training Sample Size. Chemometrics and Intelligent Laboratory Systems 211 (2021), 104269. Issue February. https://doi.org/10.1016/j.chemolab.2021.104269Google ScholarCross Ref
Recommendations
Hierarchical Means Clustering
AbstractIn the cluster analysis literature, there are several partitioning (non-hierarchical) methods for clustering multivariate objects based on model estimation. Distinct to these methods is the use of a system of n nested statistical models and the ...
Self-Organizing-Map Based Clustering Using a Local Clustering Validity Index
Classical clustering methods, such as partitioning and hierarchical clustering algorithms, often fail to deliver satisfactory results, given clusters of arbitrary shapes. Motivated by a clustering validity index based on inter-cluster and intra-cluster ...
Semi-supervised Hierarchical Clustering
ICDM '11: Proceedings of the 2011 IEEE 11th International Conference on Data MiningSemi-supervised clustering (i.e., clustering with knowledge-based constraints) has emerged as an important variant of the traditional clustering paradigms. However, most existing semi-supervised clustering algorithms are designed for partitional ...
Comments