Five task clusters that enable efficient and effective digitization of biological collections

Nelson, Gil; Paul, Deborah; Riccardi, Greg; Mast, Austin

doi:10.3897/zookeys.209.3135

Cited by 73 publications

(60 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Metadata is always necessary to describe the content and source of the data but tends to be onerous to collect and to not remain connected to the data it describes (Wilson, 2007). We decided to create a simple metadata standard that was embedded into the filenames (Murdy et al, 2015;Nelson et al, 2012). The metadata information was chosen to ensure a unique identifier for each image file.…”

Section: From Register Books To Unique Digital Image Identifiersmentioning

confidence: 99%

From books to bytes: A new data rescue tool

Slonosky¹,

Sieber

Burr

et al. 2019

Geoscience Data Journal

View full text Add to dashboard Cite

Historical data provides observational information crucial to our understanding of the evolution of geophysical processes. However, there is a gap between predigital age observations, which are typically handwritten, and data that is discoverable and analysable. The data rescue protocols here address this gap, covering the information lifecycle from handwritten register pages to transcription‐ready content, describing the historical data, the database design for the data rescue, and the development of an application design to transcribe the meteorological information directly from an image file to the database. The preparatory steps necessary to organize, curate, image, and structure the meteorological information, prior to transcribing the historical data, are outlined here in an integrated methodology. The initial organization, the development of an image file nomenclature to link the rescued data to the original source, and the description of a metadata schema to optimize the transcription application are all vital to the process of ensuring traceability and transparency in the data rescue process. Taken together, these steps describe best practices guidelines for similar projects. Although we designed the methodology and application to be used in any data rescue context, our particular concern was to accommodate the needs of citizen scientists. We thus focused on making our application easily maintained, flexible, direct to database, clear, and simple to use. Open Practices This article has earned an Open Data badge for making publicly available the digitally‐shareable data necessary to reproduce the reported results. The data is available at https://citsci.geog.mcgill.ca. Learn more about the Open Practices badges from the Center for Open Science: https://osf.io/tvyxz/wiki.

show abstract

Section: From Register Books To Unique Digital Image Identifiersmentioning

confidence: 99%

From books to bytes: A new data rescue tool

Slonosky¹,

Sieber

Burr

et al. 2019

Geoscience Data Journal

View full text Add to dashboard Cite

show abstract

“…Following the lead of DROID, output from previous iDigBio-sponsored workflow working groups, and the digitization task clusters enumerated by Nelson et al (2012), the paleontology digitization workflows working group pursued a modular approach to workflow development. The four primary modules for which workflows were developed are listed in Figure 1.…”

Section: Digitization Workflowsmentioning

confidence: 99%

“…The development and documentation of effective workflows is a primary component in the digitization of neontological and paleontological collections (Granzow-de la Cerda and Beach, 2010;Vollmar et al, 2010;Beaman and Cellinese, 2012;Haston et al, 2012;Nelson et al, 2012;Weiss, 2013;Wolniewicz, 2009). Nevertheless, there is no current workflow documentation outlining best or recommended practices for the digitization of paleontological collections.…”

Section: Introductionmentioning

confidence: 99%

Digitization workflows for paleontology collections

Karim

Burkhalter²,

Farrell

et al. 2016

Palaeontologia Electronica

View full text Add to dashboard Cite

The development of digitization workflows is an essential part of any formalized large-scale digitization program. Paleontological collections literature has addressed the need for, and utility of, digitized collections for nearly four decades, but no modern, community-vetted set of digitization workflows to accomplish this goal has been widely adopted. With the advent of the U.S. National Science Foundation's (NSF) Advancing the Digitization of Biodiversity Collections (ADBC) program in 2011, iDigBio, NSF's national coordinating center for facilitating digitization, in collaboration with broad community representation from numerous institutions, launched a series of working groups to address workflow development across all major preparation types. Workflow modules have been developed for pre-digitization curation, data entry, imaging objects (catalogs, field notes and other materials not stored with specimens, labels, two-and three-dimensionally preserved specimens), image processing, and proactive digitization. Modules and the tasks they include may be implemented in any order and customized for specific configurations and institutional parameters. The workflows are made publicly available for download and customization at GitHub and via the iDigBio documentation pages. A review of platforms for electronic data publishing through online aggregators, a crucial step in any digitization program, is also provided.

show abstract

“…Despite the large volume of specimen images and the prior use of artificial intelligence in herbaria for tasks such as phenological scoring (Lorieul et al., ), very few applications have been developed to automate the tasks involved in image post‐processing (i.e., preparing archival images for public access and use). Recommendations for tools, as well as step‐by‐step guidelines on how to use them for image capture and manual batch image post‐processing tasks, are available on iDigBio's website (Nelson et al., ; Tulig et al., ). Among the equipment recommended for imaging is a standardized color reference chart (CRC), which may be used later for color normalization during post‐processing (Nelson et al., ).…”

mentioning

confidence: 99%

Enabling automated herbarium sheet image post‐processing using neural network models for color reference chart detection

et al. 2020

View full text Add to dashboard Cite

Premise Large‐scale efforts to digitize herbaria have resulted in more than 18 million publicly available Plantae images on sites such as iDigBio. The automation of image post‐processing will lead to time savings in the digitization of biological specimens, as well as improvements in data quality. Here, new and modified neural network methodologies were developed to automatically detect color reference charts (CRC), enabling the future automation of various post‐processing tasks. Methods and Results We used 1000 herbarium specimen images from 52 herbaria to test our novel neural network model, ColorNet, which was developed to identify CRCs smaller than 4 cm2, resulting in a 30% increase in accuracy over the performance of other state‐of‐the‐art models such as Faster R‐CNN. For larger CRCs, we propose modifications to Faster R‐CNN to increase inference speed. Conclusions Our proposed neural networks detect a range of CRCs, which may enable the automation of post‐processing tasks found in herbarium digitization workflows, such as image orientation or white balance correction.

show abstract

Five task clusters that enable efficient and effective digitization of biological collections

Cited by 73 publications

References 13 publications

From books to bytes: A new data rescue tool

From books to bytes: A new data rescue tool

Digitization workflows for paleontology collections

Enabling automated herbarium sheet image post‐processing using neural network models for color reference chart detection

Contact Info

Product

Resources

About