MétaCan
Menu
Back to cohort
Record W3199517873

Digitization Decisions: Comparing OCR Software for Librarian and Archivist Use

2021· article· en· W3199517873 on OpenAlexaboutno aff
Leanne Olson, Veronica Berry

Bibliographic record

VenueDOAJ (DOAJ: Directory of Open Access Journals) · 2021
Typearticle
Languageen
FieldArts and Humanities
TopicDigital and Traditional Archives Management
Canadian institutionsnot available
Fundersnot available
KeywordsDigitizationArchivistComputer scienceSoftwareWorld Wide WebSpecial collectionsInformation retrievalLibrary scienceProgramming languageComputer vision
DOInot available

Abstract

fetched live from OpenAlex

This paper is intended to help librarians and archivists who are involved in digitization work choose optical character recognition (OCR) software. The paper provides an introduction to OCR software for digitization projects, and shares the method we developed for easily evaluating the effectiveness of OCR software on resources we are digitizing. We tested three major OCR programs (Adobe Acrobat, ABBYY FineReader, Tesseract) for accuracy on three different digitized texts from our archives and special collections at the University of Western Ontario. Our test was divided into two parts: a word accuracy test (to determine how searchable the final documents were), and a test with a screen reader (to determine how accessible the final documents were). We share our findings from the tests and make recommendations for OCR work on digitized documents from archives and special collections.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.197
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.996
Threshold uncertainty score0.098

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.197
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0090.007
Science and technology studies0.0020.002
Scholarly communication0.0040.005
Open science0.0010.003
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.411
GPT teacher head0.472
Teacher spread0.061 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueDOAJ (DOAJ: Directory of Open Access Journals)Same topicDigital and Traditional Archives ManagementFrench-language works237,207