Identification and measurement of tropical tuna species in purse seiner catches using computer vision and deep learning

Lekunberri, Xabier; Ruiz, Jon; Quincoces, Iñaki; Dornaika, Fadi; Arganda‐Carreras, Ignacio; Fernandes, José António

doi:10.1016/j.ecoinf.2021.101495

Cited by 14 publications

(20 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like other researchers (e.g. Lekunberri et al 2022), we found that image augmentation through rotation and flips improved the image classification model performance (overall accuracy increased by 10%). The augmentation was easy, fast and straightforward and we recommend using it in most image classification and object detection applications.…”

Section: Lessons Learned Challenges and Future Applicationssupporting

confidence: 86%

“…Like other researchers (e.g. Lekunberri et al . 2022), we found that image augmentation through rotation and flips improved the image classification model performance (overall accuracy increased by 10%).…”

Section: Lessons Learned Challenges and Future Applicationssupporting

confidence: 77%

“…In addition, the time consuming process of manual annotation of images for object detection is also important to consider. In fisheries contexts, the majority of image processing and classification models aim to automatically identify fish species and are developed at the regional level, and are often fisheries-specific (Lekunberri et al 2022;Ovalle et al 2022;Palmer et al 2022). Even though groups use different techniques (such as image classification, object detection and segmentation) these individual (and regional) models could be combined into a global, hierarchical classification framework for automatically identifying fish species worldwide.…”

Section: Lessons Learned Challenges and Future Applicationsmentioning

confidence: 99%

“…In fisheries contexts, the majority of image processing and classification models aim to automatically identify fish species and are developed at the regional level, and are often fisheries-specific (Lekunberri et al . 2022; Ovalle et al .…”

Section: Lessons Learned Challenges and Future Applicationsmentioning

confidence: 99%

“…2021), this is still very limited compared to other fields and mainly applied to commercial fisheries (e.g. Lekunberri et al . 2022; Ovalle et al .…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A scalable open-source framework for machine learning based image collection, annotation and classification: a case study for automatic fish species identification

Silva

Dainys

Simmons³

et al. 2022

Preprint

View full text Add to dashboard Cite

Citizen science platforms, social media and multiple smart phone applications enable collection of large amounts of georeferenced images. This provides a huge opportunity in biodiversity and ecological research, but also creates challenges for efficient data handling and processing. Recreational and small-scale fisheries is one of the fields that could be revolutionised by efficient, widely accessible and machine learning based processing of georeferenced images. The majority of non-commercial inland and coastal fisheries are considered data poor and are rarely assessed, yet they provide multiple societal benefits and can have large ecological impacts. Given that large quantities of fish observations and images are being collected by fishers every day, artificial intelligence (AI) and computer vision applications offer a great opportunity to improve data collection, automate analyses and inform management. Yet, to date, many AI image analysis applications in fisheries are focused on the commercial sector and are not publicly available for community use. In this study we present an open-source modular framework for large scale image storage, handling, annotation and automatic classification, using cost- and labour-efficient methodologies. The tool is based on TensorFlow Lite Model Maker library and includes data augmentation and transfer learning techniques, applied to different convolutional neural network models. We demonstrate the implementation of this framework in an example case study for automatic fish species identification from images taken through a recreational fishing smartphone application. The framework presented here is highly customisable for further advancement and community based image collection and annotation.

show abstract

Section: Lessons Learned Challenges and Future Applicationssupporting

confidence: 86%

Section: Lessons Learned Challenges and Future Applicationssupporting

confidence: 77%

Section: Lessons Learned Challenges and Future Applicationsmentioning

confidence: 99%

Section: Lessons Learned Challenges and Future Applicationsmentioning

confidence: 99%

“…2021), this is still very limited compared to other fields and mainly applied to commercial fisheries (e.g. Lekunberri et al . 2022; Ovalle et al .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations