Digitisation Doctor Optical Character Recognition
Download as PPTX, PDF•3 likes•1,695 views
This document discusses Simon Tanner's online presence and several links related to optical character recognition (OCR). It lists Simon Tanner's blog and Twitter account, as well as several links to resources on evaluating OCR accuracy, including a slideshare presentation, a website, and two PDF documents from Oxford University and the Digital Library relating to OCR feasibility and measuring OCR accuracy of 19th century archived newspapers.
Digitisation Doctor Optical Character Recognition
- 1. Simon Tanner Blog: simon-tanner.blogspot.co.uk Twitter: @SimonTanner www.slideshare.net/KDCS/
- 2. King’s Digital Consultancy Services www.digitalconsultancy.net
- 3. Deciding whether Optical Character Recognition is feasible (PDF document) created for the Oxford University Digital Library www.odl.ox.ac.uk/papers/OCRFeasibility_final.pdf Measuring Mass Text Digitization Quality and Usefulness: Lessons Learned from Assessing the OCR Accuracy of the British Library's 19th Century Online Newspaper Archive www.dlib.org/dlib/july09/munoz/07munoz.html www.impact-project.eu
- 5. Uniformity Language Text alignment Complexity of alignment Lines, graphics and pictures Handwriting
- 6. Evaluating OCR accuracy is about more than just character to character accuracy rates Character accuracy rates are misleading (more later…) It is also about assessing the functionality enabled through the OCR’s output Search accuracy Volume of hits returned Ability to structure searches and results Accuracy of result ranking Amount of correction required to achieve the required performance
- 7. Consider this scenario: 1,000 words with 5,000 characters (an average of 5 per word) excluding spaces 90% character accuracy means: 4,500 characters correct Possibly a maximum 900 words correct (90%) Possibly a minimum 500 words correct (50%) Reality is somewhere in between Depending on the number of “significant words” the search results could still be almost 100% or near zero
- 9. 100 90 80 70 60 50 1801 1810 1820 1830 1840 1850 1860 1870 1880 1890 1900 characters words words with capital letter start significant words Poly. (characters) Poly. (words) Poly. (significant words) Poly. (words with capital letter start
- 12. OCR Results % characters % words correct No. of corrections OCR Engine correct FineReader 91.1 70.9 110 PrimeOCR 93.95 79.1 79 Total number of characters = 2109 Total number of words = 379 I am petfood, God toil! uttedy-toverthroW, at feaft; $gy abafe Men's affections tp; and seal for all Party-making Notions amdngft CfiriftiansybefGieirie will raife his,Church to that prof- perous, flourilhing State prophefied of, and prOmifed in the Scrip* tures. There mult be more Love, and Charity, and Unanimity amongft Chriftians,.
- 14. OCR Results % characters % words correct No. of corrections OCR Engine correct FineReader 73.7 57.5 31 PrimeOCR 75.9 62.37 28 Total number of characters = 411 Total number of words = 73 A THEATRE erein be reprc-fented as wel the miferies & calamities tijat foiioto tht too* e^jr alfo the greate toyts and plefures tobtcf) tbe fatrfc faltooenio^ An Argument both profitable and dele&able, to all that finccrcly loue the word of Codt'. *Deuifedby S. hhnv&n~ derlS^oodt. s 3^ Scene and allowed according to the order appointed. , ^ Imprinted at London by Henry Bynncman* Anno Domini. CVM PHIT
- 15. Simon Tanner Blog: simon-tanner.blogspot.co.uk Twitter: @SimonTanner