A novel automated label data extraction and data base generation system from herbarium specimen images using OCR and NER

Takano, Atsuko; Cole, Theodor C. H.; Konagai, Hajime

doi:10.1038/s41598-023-50179-0

Cited by 2 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, through online databases or other shared resources (Lendemer et al 2020;Monfils et al 2022;Hardisty et al 2023), digitisation makes museum collections more accessible to the wider scientific community and to researchers from disadvantaged or distant countries who may not have the opportunity to see the specimen in person (open science concept). The Extended Specimen Approach (ESA; Webster 2017; Lendemer et al 2020) is a method of digitisation that goes beyond the physical specimen, e.g., photographs, X-rays, CT scans (Stoev et al 2013;Akkari et al 2015Akkari et al , 2018, but also includes all its attributes, such as historical information stored in the collection in the form of acquisition and inventory books, inventory cards and labels (Haston et al 2012;Albano et al 2018;Price et al 2018;Zahiri et al 2021;Bogutskaya et al 2022;Takano et al 2024).…”

Section: Introductionmentioning

confidence: 99%

An annotated catalogue of selected historical type specimens, including genetic data, housed in the Natural History Museum Vienna

Palandačić,

Chai,

Shandikov

et al. 2024

View full text Add to dashboard Cite

Museum collections are an important source for resolving taxonomic issues and species delimitation. Type specimens as name-bearing specimens, traditionally used in morphology-based taxonomy, are, due to the progress in historical DNA methodology, increasingly used in molecular taxonomic studies. Museum collections are subject to constant deterioration and major disasters. The digitisation of collections offers a partial solution to these problems and makes museum collections more accessible to the wider scientific community. The Extended Specimen Approach (ESA) is a method of digitisation that goes beyond the physical specimen to include the historical information stored in the collection. The collections of the Natural History Museum Vienna represent one of the largest non-university research centres in Europe and, due to their size and numerous type specimens, are frequently used for taxonomic studies by visiting and resident scientists. Recently, a version of ESA was presented in the common catalogue of the Fish and Evertebrata Varia collections and extended to include genetic information on type specimens in a case study of a torpedo ray. Here the case study was extended to a heterogeneous selection of historical type series from different collections with the type locality of Vienna. The goal was to apply the ESA, including genetic data on a selected set of type material: three parasitic worms, three myriapods, two insects, twelve fishes, and one bird species. Five hundred digital items (photographs, X-rays, scans) were produced, and genetic analysis was successful in eleven of the 21 type series. In one case a complete mitochondrial genome was assembled, and in another case ten short fragments (100–230 bp) of the cytochrome oxidase I gene were amplified and sequenced. For five type series, genetic analysis confirmed their taxonomic status as previously recognised synonyms, and for one the analysis supported its status as a distinct species. For two species, genetic information was provided for the first time. This catalogue thus demonstrates the usefulness of ESA in providing digitised data of types that can be easily made available to scientists worldwide for further study.

show abstract

Section: Introductionmentioning

confidence: 99%

An annotated catalogue of selected historical type specimens, including genetic data, housed in the Natural History Museum Vienna

Palandačić,

Chai,

Shandikov

et al. 2024

View full text Add to dashboard Cite

show abstract

Ensemble automated approaches for producing high quality herbarium digital records

Guralnick,

LaFrance,

Allen

et al. 2024

Preprint

View full text Add to dashboard Cite

One of the slowest steps in digitizing natural history collections is converting labels associated with specimens into a digital data record usable for collections management and research. Recent work has shown a path for semi-automated approaches that can find labels, OCR them and convert the raw OCR text into digital data records. Here we address how raw OCR can be converted into a digital data record via extraction into standardized Darwin Core fields. We first showcase development of a rule-based approach and compare outcomes with a large language model-based approach, in particular ChatGPT4. We next quantified error rates in a set of OCRed labels, determining omission and commission errors for both approaches and documenting other issues. For example, we find that ChatGPT4 will often create field names that are not Darwin Core compliant. Our results suggest that these approaches each have different limitations. Therefore, we developed an ensemble approach that utilizes outputs from both in order to reduce problems from each individual method. An ensemble method reduces issues with field name heterogeneity and strongly reduces information extraction errors. This suggests that such an ensemble method is likely to have particular value for creating digital data records, even for complicated label content, given that longer labels, though more error prone, are still successfully extracted. While human validation is still much needed to ensure the best possible quality, we showcase working solutions to speed digitization of herbarium specimen labels that are likely usable more broadly for all natural history collection types.

show abstract

A novel automated label data extraction and data base generation system from herbarium specimen images using OCR and NER

Cited by 2 publications

References 21 publications

An annotated catalogue of selected historical type specimens, including genetic data, housed in the Natural History Museum Vienna

An annotated catalogue of selected historical type specimens, including genetic data, housed in the Natural History Museum Vienna

Ensemble automated approaches for producing high quality herbarium digital records

Contact Info

Product

Resources

About