Automatic interpretation of otoliths using deep learning
| العنوان: | Automatic interpretation of otoliths using deep learning |
|---|---|
| المؤلفون: | Nils Olav Handegard, Alf Harbitz, Endre Moen, Vaneeda Allken, Ole Thomas Albert, Ketil Malde |
| المصدر: | PLoS ONE PLoS ONE, Vol 13, Iss 12, p e0204713 (2018) |
| سنة النشر: | 2018 |
| مصطلحات موضوعية: | 0106 biological sciences, Computer science, Flounder, computer.software_genre, Otolith, 01 natural sciences, Convolutional neural network, Machine Learning, Animal Cells, Reading (process), Image Processing, Computer-Assisted, Medicine and Health Sciences, Population dynamics of fisheries, media_common, Neurons, education.field_of_study, Multidisciplinary, Artificial neural network, Cognitive neuroscience of visual object recognition, Software Engineering, medicine.anatomical_structure, Inner Ear, Engineering and Technology, Medicine, Anatomy, Cellular Types, Research Article, Computer and Information Sciences, Neural Networks, Imaging Techniques, Process (engineering), media_common.quotation_subject, Science, Population, Image processing, Image Analysis, Research and Analysis Methods, Machine learning, 010603 evolutionary biology, Otolithic Membrane, Deep Learning, Artificial Intelligence, medicine, Animals, education, Preprocessing, business.industry, 010604 marine biology & hydrobiology, Deep learning, Biology and Life Sciences, Cell Biology, Models, Theoretical, Ears, Cellular Neuroscience, Neural Networks, Computer, Artificial intelligence, business, Head, computer, Neuroscience |
| الوصف: | The age structure of a fish population has important implications for recruitment processes and population fluctuations, and is key input to fisheries assessment models. The current method relies on manually reading age from otoliths, and the process is labor intensive and dependent on specialist expertise.Advances in machine learning have recently brought forth methods that have been remarkably successful in a variety of settings, with potential to automate analysis that previously required manual curation. Machine learning models have previously been successfully applied to object recognition and similar image analysis tasks. Here we investigate whether deep learning models can also be used for estimating the age of otoliths from images.We adapt a standard neural network model designed for object recognition to the task of estimating age from otolith images. The model is trained and validated on a large collection of images of Greenland halibut otoliths. We show that the model works well, and that its precision is comparable to and may even surpass that of human experts.Automating this analysis will help to improve consistency, lower cost, and increase scale of age prediction. Similar approaches can likely be used for otoliths from other species as well as for reading fish scales. The method is therefore an important step forward for improving the age structure estimates of fish populations. |
| وصف الملف: | application/pdf |
| اللغة: | English |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9937b6fa650d12e1f0b220daed7ed076 http://hdl.handle.net/11250/2588960 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....9937b6fa650d12e1f0b220daed7ed076 |
| قاعدة البيانات: | OpenAIRE |
| الوصف غير متاح. |