Schrödinger’s phenotypes: herbarium specimens show two-dimensional images are both good and (not so) bad sources of morphological data

Borges, Leonardo Maurici; Reis, Victor; Izbicki, Rafael

doi:10.1101/2020.03.31.018812

Cited by 5 publications

(6 citation statements)

References 87 publications

(102 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Localisation of plant organs will improve automated recognition and measurements of organ-specific traits, by preselecting appropriate training material for these approaches. The general approach of measuring traits from images instead of the specimen itself has been shown to be precise, except for very small objects (Borges et al 2020). Of course, measurements that involve further processing of plant parts, as often done in traditional morphological studies on herbarium specimens, are not possible from images.…”

Section: Discussionmentioning

confidence: 99%

Detection and annotation of plant organs from digitised herbarium scans using deep learning

Younis¹,

Schmidt²,

Weiland³

et al. 2020

BDJ

View full text Add to dashboard Cite

As herbarium specimens are increasingly becoming digitised and accessible in online repositories, advanced computer vision techniques are being used to extract information from them. The presence of certain plant organs on herbarium sheets is useful information in various scientific contexts and automatic recognition of these organs will help mobilise such information. In our study, we use deep learning to detect plant organs on digitised herbarium specimens with Faster R-CNN. For our experiment, we manually annotated hundreds of herbarium scans with thousands of bounding boxes for six types of plant organs and used them for training and evaluating the plant organ detection model. The model worked particularly well on leaves and stems, while flowers were also present in large numbers in the sheets, but were not equally well recognised.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection and annotation of plant organs from digitised herbarium scans using deep learning

Younis¹,

Schmidt²,

Weiland³

et al. 2020

BDJ

View full text Add to dashboard Cite

show abstract

“…and functional trait, phylogenetic, and collector characteristics that must be taken into account when using specimen data and datasets (Meyer et al, 2016;Daru et al, 2018;Cornwell et al, 2019;Nic Lughadha et al, 2019). Moreover, the accuracy of a herbarium's automated image analysis decreases as traits diminish in size, at lower resolution, and if organs overlap (Borges et al, 2020). Phenological determination using machine learning is limited by factors such as damage obscuring certain traits, material being stored in opaque packets and the morphological characteristics of some species (e.g.…”

Section: Reviewmentioning

confidence: 99%

“…While in the past we could get information only from looking at the physical specimens, our technical and technological ability to extract data from the specimens (e.g. from images (Borges et al, 2020)) makes this virtual information increasingly important. In other words, virtual data will enrich (rather than replace) the information provided by the physical objects themselves, with collections providing the essential first step to a new way of understanding plant diversity, ecology and physiology.…”

Section: Conclusion and Future Perspectivesmentioning

confidence: 99%

Reversing extinction trends: new uses of (old) herbarium specimens to accelerate conservation action on threatened species

et al. 2021

View full text Add to dashboard Cite

Summary Although often not collected specifically for the purposes of conservation, herbarium specimens offer sufficient information to reconstruct parameters that are needed to designate a species as ‘at‐risk’ of extinction. While such designations should prompt quick and efficient legal action towards species recovery, such action often lags far behind and is mired in bureaucratic procedure. The increase in online digitization of natural history collections has now led to a surge in the number new studies on the uses of machine learning. These repositories of species occurrences are now equipped with advances that allow for the identification of rare species. The increase in attention devoted to estimating the scope and severity of the threats that lead to the decline of such species will increase our ability to mitigate these threats and reverse the declines, overcoming a current barrier to the recovery of many threatened plant species. Thus far, collected specimens have been used to fill gaps in systematics, range extent, and past genetic diversity. We find that they also offer material with which it is possible to foster species recovery, ecosystem restoration, and de‐extinction, and these elements should be used in conjunction with machine learning and citizen science initiatives to mobilize as large a force as possible to counter current extinction trends.

show abstract

“…Of particular interest is biological specimen image collections, given their value as a data source for species identification and morphological study [ 6 , 7 ]. The research presented in this paper addresses this topic in the context of an NSF supported Harnessing the Data Revolution (HDR) project, Biology-Guided Neural Networks for Discovering Phenotypic Traits (BGNN).…”

Section: Introductionmentioning

confidence: 99%

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

Leipzig

Bakis

Wang

et al. 2021

Metadata and Semantic Research

View full text Add to dashboard Cite

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.

show abstract

Schrödinger’s phenotypes: herbarium specimens show two-dimensional images are both good and (not so) bad sources of morphological data

Cited by 5 publications

References 87 publications

Detection and annotation of plant organs from digitised herbarium scans using deep learning

Detection and annotation of plant organs from digitised herbarium scans using deep learning

Reversing extinction trends: new uses of (old) herbarium specimens to accelerate conservation action on threatened species

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

Contact Info

Product

Resources

About