Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Floralens: a Deep Learning Model for the Portuguese Native Flora (2403.12072v2)

Published 13 Feb 2024 in cs.CV and cs.LG

Abstract: Machine-learning techniques, especially deep convolutional neural networks, are pivotal for image-based identification of biological species in many Citizen Science platforms. In this paper, we describe the construction of a dataset for the Portuguese native flora based on publicly available research-grade datasets, and the derivation of a high-accuracy model from it using off-the-shelf deep convolutional neural networks. We anchored the dataset in high-quality data provided by Sociedade Portuguesa de Bot^anica and added further sampled data from research-grade datasets available from GBIF. We find that with a careful dataset design, off-the-shelf machine-learning cloud services such as Google's AutoML Vision produce accurate models, with results comparable to those of Pl@ntNet, a state-of-the-art citizen science platform. The best model we derived, dubbed Floralens, has been integrated into the public website of Project Biolens, where we gather models for other taxa as well. The dataset used to train the model is also publicly available on Zenodo.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Citizen Science: A Developing Tool for Expanding Science Knowledge and Scientific Literacy. BioScience, 59(11):977–984, December 2009.
  2. S. Altrudi. Connecting to nature through tech? The case of the iNaturalist app. Convergence, 27(1):124–141, 2021.
  3. M. Schermer and L. Hogeweg. Supporting citizen scientists with automatic species identification using deep learning image recognition models. Biodiversity Information Science and Standards, 2018.
  4. Pl@ntNet app in the era of deep learning. In International Conference on Learning Representations, Toulon, France, 2017.
  5. J. Wäldchen and P. Mäder. Machine learning for image based species identification. Methods in Ecology and Evolution, 9(11):2216–2225, 2018.
  6. Perspectives in machine learning for wildlife conservation. Nature Communications, 13(1):792, 2022.
  7. Applications for deep learning in ecology. Methods in Ecology and Evolution, 10(10):1632–1644, 2019.
  8. The Flora Incognita app–interactive plant species identification. Methods in Ecology and Evolution, 12(7):1335–1342, 2021.
  9. Biolens. https://rubisco.dcc.fc.up.pt/biolens. Accessed September 2022.
  10. Identificação taxonómica em biologia usando inteligência artificial. Revista de Ciência Elementar - Casa das Ciências, December 2022.
  11. M. Marques. A Portuguese Flora Identification Tool Using Deep Learning. Master’s thesis, Masters thesis, Faculty of Sciences, University of Porto, 2021.
  12. A. Filgueiras. Floralens: a deep learning model for portuguese flora. Master’s thesis, Masters thesis, Faculty of Sciences, University of Porto, 2022.
  13. T. Mamede. On using Deep Learning for Automatic Taxonomic Identification of Butterflies. Master’s thesis, BSC project report, Faculty of Sciences, University of Porto, 2020.
  14. Deep-plant: Plant identification with convolutional neural networks. In IEEE International Conference on Image Processing, pages 452–456, 2015.
  15. I. Heredia. Large-scale plant classification with deep neural networks. In Computing Frontiers Conference, pages 259–262, 2017.
  16. Deep learning for plant identification in natural environment. Computational Intelligence and Neuroscience, 2017.
  17. Plant identification: Experts vs. machines in the era of deep learning: deep learning techniques challenge flora experts. Multimedia Tools and Applications for Environmental & Biodiversity Informatics, pages 131–149, 2018.
  18. AI Nature Services. https://ainature.eu/. Accessed September 2022.
  19. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations, Virtual Conference, 2021.
  20. Are Transformers more robust than CNNs? In Advances in Neural Information Processing Systems, pages 26831–26843, 2021.
  21. The GBIF integrated publishing toolkit: facilitating the efficient publishing of biodiversity data on the Internet. PLOS One, 9(8), 2014.
  22. AI-GeoSpecies: integrate artificial intelligence into your citizen science app. https://doi.org/10.5281/zenodo.7657594, February 2023.
  23. WCVP: World Checklist of Vascular Plants. http://sftp.kew.org/pub/data-repositories/WCVP/. Accessed September 2023.
  24. Acquiring and preprocessing leaf images for automated plant identification: understanding the tradeoff between effort and information gain. Plant Methods, 13(1):1–11, 2017.
  25. Flowers, leaves or both? how to obtain suitable images for automated plant identification. Plant Methods, 15(1):1–11, 2019.
  26. The iNaturalist species classification and detection dataset. In IEEE Conference on Computer Vision and Pattern Recognition, pages 8769–8778, 2018.
  27. Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017). In Conference and Labs of the Evaluation Forum, 2017.
  28. Overview of PlantCLEF 2022: Image-based plant identification at global scale. In Conference and Labs of the Evaluation Forum, volume 3180, pages 1916–1928, 2022.
  29. iNaturalist contributors, iNaturalist (2022). iNaturalist research-grade observations. iNaturalist.org. https://doi.org/10.15468/ab3s5x. Accessed via GBIF.org on July 2023.
  30. H. de Vries and M. Lemmens. Observation.org, nature data from around the world. https://doi.org/10.15468/5nilie. Accessed via GBIF.org on July 2023.
  31. Pl@ntnet observations. Version 1.2. Pl@ntNet. https://doi.org/10.15468/gtebaa. Accessed via GBIF on July 2023.
  32. The GBIF integrated publishing toolkit: facilitating the efficient publishing of biodiversity data on the internet. PLOS One, 9(8), 2014.
  33. Validation. https://observation.org/pages/validation/. Accessed July 2023.
  34. iNaturalist. What is the data quality assessment and how do observations qualify to become “research grade”? https://www.inaturalist.org/pages/help#quality. Accessed July 2023.
  35. E. Bisong. Google AutoML: Cloud Vision, pages 581–598. Apress, 2019.
  36. AutoML Vision Documentation. https://cloud.google.com/vision/automl/docs/. Accessed July 2023.
  37. TensorFlow Lite, ML for Mobile and Edge Devices. https://www.tensorflow.org/lite/. Accessed July 2023.
  38. TensorFlow.js, Machine Learning for Javascript developers. https://www.tensorflow.org/js/. Accessed July 2023.
  39. Mnasnet: Platform-aware neural architecture search for mobile. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2815–2823, 2019.
  40. Plantclef2022, image-based plant identification at global scale. https://www.imageclef.org/PlantCLEF2022. Accessed July 2023.
  41. Pl@ntNet API for developers. https://my.plantnet.org. Accessed July 2023.
  42. PlantCLEF’22 trusted training set. https://lab.plantnet.org/LifeCLEF/PlantCLEF2022/train. Accessed July 2023.
  43. Wikimedia REST API. Accessed July 2023.
  44. Pl@ntNet. Pl@ntNet news – Covering all countries floras and new identification AI. https://plantnet.org/en/2023/07/05/covering-all-countries-floras-new-identification-ai/. Accessed September 2023.
  45. The Floralens Dataset for Portuguese Flora. https://doi.org/10.5281/zenodo.10639701. Accessed February 2024.
  46. Encyclopedia Of Life Datasets. https://opendata.eol.org/dataset. Accessed November 2023.
  47. Royal Botanical Gardens, Kew: Plants of the World Online: Chamaeleon gummifer. https://powo.science.kew.org/taxon/urn:lsid:ipni.org:names:192416-1. Accessed July 2023.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now