In Codice Ratio
{{Short description|OCR research project}}
{{Multiple issues|{{Third-party|date=March 2021}}{{primary sources|date=March 2021}}}}
In Codice Ratio is a research project designed to study and use novel techniques such as Optical Character Recognition and Artificial Intelligence to digitize works in the Vatican Apostolic Archive,{{cite book|last1=Firmani|first1=Donatella|last2=Maiorino|first2=Marco|last3=Merialdo|first3=Paolo|last4=Nieddu|first4=Elena|date=2018-03-01|title=Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining|chapter=Towards Knowledge Discovery from the Vatican Secret Archives. In Codice Ratio - Episode 1|pages=263–272|doi=10.1145/3219819.3219879|arxiv=1803.03200|isbn=9781450355520|s2cid=3772349}}{{Cite web|title=Towards Knowledge Discovery from the Vatican Secret Archives. In Codice Ratio|url=https://www.kdd.org/kdd2018/accepted-papers/view/towards-knowledge-discovery-from-the-vatican-secret-archives.-in-codic2|access-date=2021-03-25|website=SIGKDD - KDD 2018|language=en}} most of which is handwritten.{{Cite web|last=Kean|first=Sam|date=2018-04-30|title=Artificial Intelligence Is Cracking Open the Vatican's Secret Archives|url=https://www.theatlantic.com/technology/archive/2018/04/vatican-secret-archives-artificial-intelligence/559205/|access-date=2021-03-25|website=The Atlantic|language=en}}{{cite web |url=https://www.researchgate.net/publication/322096820 |title=In Codice Ratio: OCR of Handwritten Latin Documents using Deep Convolutional Networks |first1=Donatella |last1=Firmani
|first2=Paolo |last2=Merialdo |first3=Elena |last3=Nieddu |first4=Simone |last4=Scardapane |date=December 2017}}
History
In 2017, a project based in Roma Tre University called In Codice Ratio began using artificial intelligence and optical character recognition to attempt to transcribe more documents from the archives.{{cite web | last1=Firmani |first1= D. | last2=Merialdo |first2= P. |last3=Nieddu |first3=E. |last4=Scardapane | first4=S. |title=In codice ratio: OCR of handwritten Latin documents using deep convolutional networks | publisher = International Workshop on Artificial Intelligence for Cultural Heritage| pages= 9–16 | date= 2017 |url = http://ceur-ws.org/Vol-2034/paper_2.pdf }} While character-recognition software is adept at reading typed text, the cramped and many-serifed style of medieval handwriting makes distinguishing individual characters difficult for the software.{{Cite news| date= 15 March 2018 | url=https://www.technologyreview.com/s/610530/ai-tackles-the-vaticans-secrets/|title=AI tackles the Vatican's secrets |work=MIT Technology Review|access-date=27 November 2018 | language=en}} Many individual letters of the alphabet are often confused by human readers of medieval handwriting, let alone a computer program. The team behind In Codice Ratio tried to solve this problem by developing a machine-learning software that could parse this handwriting. Their program eventually achieved 96% accuracy in parsing this type of text.{{cite web|url=https://ercim-news.ercim.eu/en111/special/in-codice-ratio-scalable-transcription-of-vatican-registers|title=In Codice Ratio: Scalable Transcription of Vatican Registers|website=ERCIM News | language=en-gb| date= 25 September 2017 |first1= Donatella |last1= Firmani | first2= Paolo |last2= Merialdo |first3= Marco |last3= Maiorino | access-date=27 November 2018}}
References
{{reflist}}
External links
- [http://www.inf.uniroma3.it/db/icr Official site]
{{authority control}}