Coral species identification with texture or structure images using a two-level classifier based on Convolutional Neural Networks

Gómez-Ríos, Anabel; Tabik, Siham; Luengo, Julián; Shihavuddin, Asm; Herrera, Francisco

doi:10.1016/j.knosys.2019.104891

Cited by 37 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detection and classification of marine growth from images using deep learning have been investigated in various studies with a focus ranging from the classification of species in coral reefs [43], to bio-fouling under vessels [44], [45] and finally marine fouling on offshore structures [9], [46]. As with the sensor technologies presented in the previous section, the underwater environment poses a challenge in the classification of marine growth due to the risk of poor image quality in both training images and inspection campaigns, caused by water turbidity.…”

Section: Marine Growth Classification Methodsmentioning

confidence: 99%

On the Autonomous Inspection and Classification of Marine Growth on Subsea Structures

Liniger

Jensen

Pedersen

et al. 2022

OCEANS 2022 - Chennai

View full text Add to dashboard Cite

Section: Marine Growth Classification Methodsmentioning

confidence: 99%

On the Autonomous Inspection and Classification of Marine Growth on Subsea Structures

Liniger

Jensen

Pedersen

et al. 2022

OCEANS 2022 - Chennai

View full text Add to dashboard Cite

“…is method can fuse the features of different layers from images by neural network to further improve the quality of learning features. Gómez-Ríos et al [45] built a classifier which can use two kinds of images, namely, texture image and structure image, to identify the species of corals. e method first identifies whether the input image is texture image or structure image by a ResNet model, and then constructs a ResNet model for texture image and structure image, respectively, to identify coral species.…”

Section: Feature Fusionmentioning

confidence: 99%

A Feature Fusion Method with Guided Training for Classification Tasks

Zhang

Fan

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In this paper, a feature fusion method with guiding training (FGT-Net) is constructed to fuse image data and numerical data for some specific recognition tasks which cannot be classified accurately only according to images. The proposed structure is divided into the shared weight network part, the feature fused layer part, and the classification layer part. First, the guided training method is proposed to optimize the training process, the representative images and training images are input into the shared weight network to learn the ability that extracts the image features better, and then the image features and numerical features are fused together in the feature fused layer to input into the classification layer for the classification task. Experiments are carried out to verify the effectiveness of the proposed model. Loss is calculated by the output of both the shared weight network and classification layer. The results of experiments show that the proposed FGT-Net achieves the accuracy of 87.8%, which is 15% higher than the CNN model of ShuffleNetv2 (which can process image data only) and 9.8% higher than the DNN method (which processes structured data only).

show abstract

“…RSMAS, StructureRSMAS and EILAT are small coral data sets. RSMAS and EILAT [22,2] are texture data sets, containing coral patches, meaning that they are close-up patches extracted from larger images, and StructureRSMAS [23] is a structure data set, containing images of entire corals. The patches in EILAT have size 64×64 and come from images taken under similar underwater conditions, and the ones in RSMAS have size 256×256 and come from images taken under different conditions.…”

Section: Data Setsmentioning

confidence: 99%

A robust approach for deep neural networks in presence of label noise: relabelling and filtering instances during training

Gómez-Ríos¹,

Luengo²,

Herrera³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning has outperformed other machine learning algorithms in a variety of tasks, and as a result, it has become more and more popular and used. However, as other machine learning algorithms, deep learning, and convolutional neural networks (CNNs) in particular, perform worse when the data sets present label noise. Therefore, it is important to develop algorithms that help the training of deep networks and their generalization to noise-free test sets. In this paper, we propose a robust training strategy against label noise, called RAFNI, that can be used with any CNN. This algorithm filters and relabels instances of the training set based on the predictions and their probabilities made by the backbone neural network during the training process. That way, this algorithm improves the generalization ability of the CNN on its own. RAFNI consists of three mechanisms: two mechanisms that filter instances and one mechanism that relabels instances. In addition, it does not suppose that the noise rate is known nor does it need to be estimated. We evaluated our algorithm using different data sets of several sizes and characteristics. We also compared it with state-of-the-art models using the CIFAR10 and CIFAR100 benchmarks under different types and rates of label noise and found that RAFNI achieves better results in most cases.

show abstract

Coral species identification with texture or structure images using a two-level classifier based on Convolutional Neural Networks

Cited by 37 publications

References 23 publications

On the Autonomous Inspection and Classification of Marine Growth on Subsea Structures

On the Autonomous Inspection and Classification of Marine Growth on Subsea Structures

A Feature Fusion Method with Guided Training for Classification Tasks

A robust approach for deep neural networks in presence of label noise: relabelling and filtering instances during training

Contact Info

Product

Resources

About