Skip to main content
Top
Published in:

2021 | OriginalPaper | Chapter

Biodiversity Image Quality Metadata Augments Convolutional Neural Network Classification of Fish Species

Authors : Jeremy Leipzig, Yasin Bakis, Xiaojun Wang, Mohannad Elhamod, Kelly Diamond, Wasila Dahdul, Anuj Karpatne, Murat Maga, Paula Mabee, Henry L. Bart Jr., Jane Greenberg

Published in: Metadata and Semantic Research

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Biodiversity image repositories are crucial sources for training machine learning approaches to support biological research. Metadata about object (e.g. image) quality is a putatively important prerequisite to selecting samples for these experiments. This paper reports on a study demonstrating the importance of image quality metadata for a species classification experiment involving a corpus of 1935 fish specimen images which were annotated with 22 metadata quality properties. A small subset of high quality images produced an F1 accuracy of 0.41 compared to 0.35 for a taxonomically matched subset low quality images when used by a convolutional neural network approach to species identification. Using the full corpus of images revealed that image quality differed between correctly classified and misclassified images. We found anatomical feature visibility was the most important quality feature for classification accuracy. We suggest biodiversity image repositories consider adopting a minimal set of image quality metadata to support machine learning.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Han, H., Giles, C.L., Manavoglu, E., et al.: Automatic document metadata extraction using support vector machines. In: 2003 Joint Conference on Digital Libraries, 2003. Proceedings, pp, 37–48 (2003) Han, H., Giles, C.L., Manavoglu, E., et al.: Automatic document metadata extraction using support vector machines. In: 2003 Joint Conference on Digital Libraries, 2003. Proceedings, pp, 37–48 (2003)
2.
go back to reference Schelter, S., Boese, J.-H., Kirschnick, J., et al.: Automatically tracking metadata and provenance of machine learning experiments. In: Machine Learning Systems workshop at NIPS (2017) Schelter, S., Boese, J.-H., Kirschnick, J., et al.: Automatically tracking metadata and provenance of machine learning experiments. In: Machine Learning Systems workshop at NIPS (2017)
3.
go back to reference Leipzig, J., Nüst, D., Hoyt, C.T., et al.: The role of metadata in reproducible computational research. arXiv [cs.DL] (2020) Leipzig, J., Nüst, D., Hoyt, C.T., et al.: The role of metadata in reproducible computational research. arXiv [cs.DL] (2020)
4.
go back to reference Ellen, J.S., Graff, C.A., Ohman, M.D.: Improving plankton image classification using context metadata. Limnol. Oceanogr. Methods 2, 17 (2019) Ellen, J.S., Graff, C.A., Ohman, M.D.: Improving plankton image classification using context metadata. Limnol. Oceanogr. Methods 2, 17 (2019)
5.
go back to reference Tang, K., Paluri, M., Fei-Fei, L., et al.: Improving image classification with location context. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1008–1016 (2015) Tang, K., Paluri, M., Fei-Fei, L., et al.: Improving image classification with location context. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1008–1016 (2015)
7.
go back to reference Hernández-Serna, A., Jiménez-Segura, L.F.: Automatic identification of species with neural networks. PeerJ 2, e563 (2014)CrossRef Hernández-Serna, A., Jiménez-Segura, L.F.: Automatic identification of species with neural networks. PeerJ 2, e563 (2014)CrossRef
8.
go back to reference Willis, C., Greenberg, J., White, H.: Analysis and synthesis of metadata goals for scientific data. J Am Soc Inf Sci Technol 63, 1505–1520 (2012)CrossRef Willis, C., Greenberg, J., White, H.: Analysis and synthesis of metadata goals for scientific data. J Am Soc Inf Sci Technol 63, 1505–1520 (2012)CrossRef
9.
go back to reference Greenberg, J.: Understanding metadata and metadata schemes. Cataloging Classif. Q. 40, 17–36 (2005)CrossRef Greenberg, J.: Understanding metadata and metadata schemes. Cataloging Classif. Q. 40, 17–36 (2005)CrossRef
10.
go back to reference Bidgood, W.D., Jr., Horii, S.C.: Introduction to the ACR-NEMA DICOM standard. Radiographics 12, 345–355 (1992)CrossRef Bidgood, W.D., Jr., Horii, S.C.: Introduction to the ACR-NEMA DICOM standard. Radiographics 12, 345–355 (1992)CrossRef
11.
go back to reference Bukhari, A.C., Nagy, M.L., Krauthammer, M., et al.: BIM: an open ontology for the annotation of biomedical images. In: ICBO (2015) Bukhari, A.C., Nagy, M.L., Krauthammer, M., et al.: BIM: an open ontology for the annotation of biomedical images. In: ICBO (2015)
12.
go back to reference Temal, L., Lando, P., Gibaud, B., et al.: OntoNeuroBase: a multi-layered application ontology in neuroimaging. In: Second Workshop: Formal Ontologies Meet Industry (FOMI 2006) (2006) Temal, L., Lando, P., Gibaud, B., et al.: OntoNeuroBase: a multi-layered application ontology in neuroimaging. In: Second Workshop: Formal Ontologies Meet Industry (FOMI 2006) (2006)
16.
go back to reference Paszke, A., Gross, S., Massa, F., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., et al. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp 8026–8037. Curran Associates, Inc. (2019) Paszke, A., Gross, S., Massa, F., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., et al. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp 8026–8037. Curran Associates, Inc. (2019)
17.
go back to reference Marcel, S., Rodriguez, Y.: Torchvision the machine-vision package of torch. In: In: Proceedings of the 18th ACM international conference on Multimedia, pp. 1485–1488. Association for Computing Machinery, New York (2010) Marcel, S., Rodriguez, Y.: Torchvision the machine-vision package of torch. In: In: Proceedings of the 18th ACM international conference on Multimedia, pp. 1485–1488. Association for Computing Machinery, New York (2010)
18.
go back to reference Avants, B.B., Kandel, B.M., Duda, J.T., et al.: ANTsR: ANTs in R: quantification tools for biomedical images. R package version 0542 (2019) Avants, B.B., Kandel, B.M., Duda, J.T., et al.: ANTsR: ANTs in R: quantification tools for biomedical images. R package version 0542 (2019)
20.
go back to reference Shyu, C.R., Brodley, C.E., Kak, A.C., et al.: Local versus global features for content-based image retrieval. In: Proceedings, IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173), pp 30–34 (1998) Shyu, C.R., Brodley, C.E., Kak, A.C., et al.: Local versus global features for content-based image retrieval. In: Proceedings, IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173), pp 30–34 (1998)
21.
go back to reference Vogel, J., Schwaninger, A., Wallraven, C.: Categorization of natural scenes: local vs. global information. In: Proceedings of Conference Army Physicians Cent Mediterr Forces (2006) Vogel, J., Schwaninger, A., Wallraven, C.: Categorization of natural scenes: local vs. global information. In: Proceedings of Conference Army Physicians Cent Mediterr Forces (2006)
Metadata
Title
Biodiversity Image Quality Metadata Augments Convolutional Neural Network Classification of Fish Species
Authors
Jeremy Leipzig
Yasin Bakis
Xiaojun Wang
Mohannad Elhamod
Kelly Diamond
Wasila Dahdul
Anuj Karpatne
Murat Maga
Paula Mabee
Henry L. Bart Jr.
Jane Greenberg
Copyright Year
2021
DOI
https://doi.org/10.1007/978-3-030-71903-6_1