Automatic interpretation of salmon scales using deep learning

Vabø, Rune; Moen, Endre; Smoliński, Szymon; Husebø, Åse; Handegard, Nils Olav; Malde, Ketil

doi:10.1016/j.ecoinf.2021.101322

Cited by 18 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the emergence of DL, several studies have been demonstrated to perform well on automatically predicting fish age from otolith images [10][11][12][13][14]. An important topic of this work was to assess whether a suitable performance from a DL system could be maintained on data from the same species but acquired in a different lab.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Fish Age Determination across Different Otolith Image Labs Using Domain Adaptation

Ordoñez

Eikvil

Salberg

et al. 2022

Fishes

View full text Add to dashboard Cite

The age determination of fish is fundamental to marine resource management. This task is commonly done by analysis of otoliths performed manually by human experts. Otolith images from Greenland halibut acquired by the Institute of Marine Research (Norway) were recently used to train a convolutional neural network (CNN) for automatically predicting fish age, opening the way for requiring less human effort and availability of expertise by means of deep learning (DL). In this study, we demonstrate that applying a CNN model trained on images from one lab (in Norway) does not lead to a suitable performance when predicting fish ages from otolith images from another lab (in Iceland) for the same species. This is due to a problem known as dataset shift, where the source data, i.e., the dataset the model was trained on have different characteristics from the dataset at test stage, here denoted as target data. We further demonstrate that we can handle this problem by using domain adaptation, such that an existing model trained in the source domain is adapted to perform well in the target domain, without requiring extra annotation effort. We investigate four different approaches: (i) simple adaptation via image standardization, (ii) adversarial generative adaptation, (iii) adversarial discriminative adaptation and (iv) self-supervised adaptation. The results show that the performance varies substantially between the methods, with adversarial discriminative and self-supervised adaptations being the best approaches. Without using a domain adaptation approach, the root mean squared error (RMSE) and coefficient of variation (CV) on the Icelandic dataset are as high as 5.12 years and 28.6%, respectively, whereas by using the self-supervised domain adaptation, the RMSE and CV are reduced to 1.94 years and 11.1%. We conclude that careful consideration must be given before DL-based predictors are applied to perform large scale inference. Despite that, domain adaptation is a promising solution for handling problems of dataset shift across image labs.

show abstract

Section: Discussionmentioning

confidence: 99%

“…During the last decades, automatic techniques have been proposed to automate this tedious activity (e.g., [9]). More recently, the use of deep learning (DL) has received more and more attention with promising results shown for Greenland halibut [10,11], snapper and hoki [12], red mullet [13] and Atlantic salmon [14].…”

Section: Introductionmentioning

confidence: 99%

Automatic Fish Age Determination across Different Otolith Image Labs Using Domain Adaptation

Ordoñez

Eikvil

Salberg

et al. 2022

Fishes

View full text Add to dashboard Cite

show abstract

“…Large-scale visual inspection is reliable and highly automated. Some experts combined convolutional neural network (CNN) with transfer learning to apply it to a new prediction of fish (wild/cultured) [ 12 ]. However, the focus of this translation method is to divide sentences into words, ignoring the influence of the positional relationship between words.…”

Section: Development and Current Situation Of Machine Translation Res...mentioning

confidence: 99%

English Lexical Analysis System of Machine Translation Based on Simple Recurrent Neural Network

Zhu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the increasing communication between countries, machine translation has become an important way of communication between ethnic groups in different language systems. In order to further improve the coverage mechanism and vocabulary translation quality of the machine translation model of neural network, this paper will study the machine translation English lexical analysis system based on simple recurrent neural network. In order to improve the effect of word alignment, marking and attention mechanism are introduced into the English lexical analysis model. The experimental results show that the tagging of named entity words in the system can reduce the problem of unregistered words. Combined with the attention mechanism, it can significantly improve the effect of word alignment and label recall. It not only improves the controllability of translation but also has a positive impact on the quality of translation and its application effect in specific scenes. The evaluation of translation quality indicators shows that the system can effectively improve the accuracy and quality of Chinese-English translation.

show abstract

“…In recent years, CNNs have received increased attention for automating fish age estimation from otolith images, as shown for Greenland halibut (Reinhardtius hippoglossoides) [13,14], snapper (Pagrus auratus) and hoki (Macruronus novaezelandiae) [15], Atlantic salmon (Salmo salar) [16], and red mullet (Mullus barbatus) [17]. These studies provided evidence that deep learning could offer an automated methodology for the analysis of otolith images, although with varying levels of accuracy, and provide cost-efficient and effective support towards the sustainability and management of fishery resources.…”

Section: Introductionmentioning

confidence: 99%

“…Below, the platform and its structure are introduced; the three otolith case studies that are currently available on the platform are reviewed; and finally, the functionality of the platform is demonstrated. Norway [16] Red mullet (Mullus barbatus) 0-5+ Greece [17] 2. Materials and Methods Table 1.…”

Section: Introductionmentioning

confidence: 99%

DeepOtolith v1.0: An Open-Source AI Platform for Automating Fish Age Reading from Otolith or Scale Images

Politikos

Sykiniotis

Petasis

et al. 2022

Fishes

Self Cite

View full text Add to dashboard Cite

Every year, marine scientists around the world read thousands of otolith or scale images to determine the age structure of commercial fish stocks. This knowledge is important for fisheries and conservation management. However, the age-reading procedure is time-consuming and costly to perform due to the specialized expertise and labor needed to identify annual growth zones in otoliths. Effective automated systems are needed to increase throughput and reduce cost. DeepOtolith is an open-source artificial intelligence (AI) platform that addresses this issue by providing a web system with a simple interface that automatically estimates fish age by combining otolith images with convolutional neural networks (CNNs), a class of deep neural networks that has been a dominant method in computer vision tasks. Users can upload otolith image data for selective fish species, and the platform returns age estimates. The estimates of multiple images can be exported to conduct conclusions or further age-related research. DeepOtolith currently contains classifiers/regressors for three fish species; however, more species will be included as related work on ageing will be tested and published soon. Herein, the architecture and functionality of the platform are presented. Current limitations and future directions are also discussed. Overall, DeepOtolith should be considered as the first step towards building a community of marine ecologists, machine learning experts, and stakeholders that will collaborate to support the conservation of fishery resources.

show abstract

Automatic interpretation of salmon scales using deep learning

Cited by 18 publications

References 27 publications

Automatic Fish Age Determination across Different Otolith Image Labs Using Domain Adaptation

Automatic Fish Age Determination across Different Otolith Image Labs Using Domain Adaptation

English Lexical Analysis System of Machine Translation Based on Simple Recurrent Neural Network

DeepOtolith v1.0: An Open-Source AI Platform for Automating Fish Age Reading from Otolith or Scale Images

Contact Info

Product

Resources

About