Project Status

Most Significant Tweet To Date (3-19-2022)

…and are named T3 and T5

T3

Scan Description:
Uses the quintessential basic Tesseract sample image, 'Eurotext'. Only English OCR is enabled here, from the 100+ languages that Tesseract supports. So very interesting will be to what extent quality improves when scan repeated with more languages.
Original Image:
1206
OCR Text:
The (quick) [brown] {fox} jumps! Over the $43,456.78 #90 dog & duck/goose, as 12.5% of E-mail from [email protected] is spam. Der ,schnelle” braune Fuchs springt iiber den faulen Hund. Le renard brun «rapide» saute par-dessus le chien paresseux. La volpe marrone rapida salta sopra il cane pigro. El zorro marrén rapido salta sobre el perro perezoso. A raposa marrom ripida salta sobre o cdo preguigoso.
Terminal Output:
172-221-090-104:~ eridu$ cd '/Users/eridu/Documents/Tesseract Tests/T3' 172-221-090-104:T3 eridu$ 172-221-090-104:T3 eridu$ tesseract --tessdata-dir '/opt/local/share/tessdata' '/Users/eridu/Documents/Tesseract Tests/T3/T3.png' 'T3' -l eng --psm 3 Tesseract Open Source OCR Engine v4.1.3 with Leptonica

T5

Scan Description:
Image taken from World Wide Web. According to Margaret Barsi Greene, this was the first instance of F. Bacon surreptitiously embedding his forbidden biography into one of his published works ('The Shepheardes Calender', 1579), published under pen-name of Edmund Spenser. No image preprocessing of any kind. Totally raw image.
Original Image:
1023
OCR Text:
ERN 3 ] SV ére byes the Seents From Iles of Greece i e 1\ Ififi?&fim zf;fb,;gh M:‘b{m : i ! “Hane tothe ‘Port of Athensfent their [bippes Fraught with theminifters and inftruments Of cruell Warre : Sixty and nine that wore Their (romwnets ‘Z%gdl, from th’ Athenianbay Put forth tovard Phrygia, and their cvow is made Toranfacke Troy, within whofe firong emures e~ TheraniflydHelen, Menelaus Queene, < With wanton Paris fleepes, and that’s the Quarrell. . 7o Tenedos theycome, And the deepe-drawing Barke do there difgorge Their warlike frautage : now on Dardan Plaines | The frefly and yet conbruifed Greekes do pitch ! Their brase Pawillions, Priawns fix-gated (ity, { Dardanand Timbria, Helias, Chetas, Troien, 4nd Antenonidus Withmafsie Staples e * dnd correfponfine and fulfilling Bolts Stirre vp the Sonnes of Troy. g Now Expeétationticklingskittifh [pirits; On one and othérfide, Trolan aid Greeke, Sets allon bazard. And hither am F come, APrelogue arm'd, bt not in confidence Of Authors pen, or Ackors voyce ; but fuited e Jnlike conditions, as our Argument ; W1 To tellyou (faire Bebolders) that our Play Leapes ore the coasnt and firfHings of thofe broyles, Beginiing inthe middle : fEay ting thence awayy Towhat may bedigeftedina Play: it oo Like, or finde fanle, do as. Jmik‘ufures are, S Now good,or bad, "tis but the chance of Warres: .-
Terminal Output:
eridu$ tesseract --tessdata-dir '/opt/local/share/tessdata' '/Users/eridu/Documents/Tesseract Tests/T5/T5.png' '/Users/eridu/Documents/Tesseract Tests/T5/T5' -l eng --psm 3 Tesseract Open Source OCR Engine v4.1.3 with Leptonica Warning: Invalid resolution 0 dpi. Using 70 instead. Estimating resolution as 262

Scroll to Top