What's that Number?

Zeydy Ortiz, Ph. D. - zortiz@datacrunchlab.com

What's available?

From “The new Tesseract package: High Quality OCR in R https://ropensci.org/blog/blog/2016/11/16/tesseract

# for Windows or Mac
install.packages("tesseract")

# On Linux you first need to install libtesseract which ships with every popular 
# distribution (Debian, Ubuntu, Fedora, CentOS, etc).

library(tesseract)
text <- ocr("http://jeroenooms.github.io/images/testocr.png")

Result

This is a lot of 12 point text to test the
ocr code and see if it works on all types
of file format.

The quick brown dog jumped over the
lazy fox. The quick brown dog jumped
over the lazy fox. The quick brown dog
jumped over the lazy fox. The quick
brown dog jumped over the lazy fox.

Original image: test image

Context matters

Original image: inlove image

text <- ocr("http://jeroenooms.github.io/files/inlove.png")
cat(text)

In love

Image quality matters

Original image: dog_lq image

Low quality image is not readable

Dog
Fm m, me use W
Tins made )5 about me aomesuo aog For related speaes Imown as "dogs", see Camdae For Other uses, see Dag
"Dogg)e"IedIIec{s here Folme uamsn must, see Daggre (arm)
The domestic dog {Cams lupus rammans or Cams [Emma/Is)“ s 2 member 0' genus cams {canines) Inzl lorms pan
onne wolHIke cams“! and 5 me most wney abundant canmore ““5"“! The dog and me extant gray wonzre ssler
laxammm wnn modern wolves not closely related Io me wolves that were <U+FB01>rst domesticated I‘ll?! smoe ns
domestication, me dog has been seleclwely bred over mlllennla [or vznous benzvms, sensory capamlmes, 2nd
pnysxzal zllnbules “"1
Their long assoclallon wnn humans has led Io dogs belllg umquely zlluned Io numzn benzvmm‘ and are me lo
Hume on 2 slarcnrncn dlel much would be Inadequate [or other can} speoes “1| Dogs are ago the oldest
domesticated ammal Dogs vzly wney m shape, SlZe and colours “3! Dogs pe<U+FB02>orm many roles [or people, such as
nummg, nemmg, puumg loads, prolecllon, asslsllllg pollce 2nd mnnary, companlonsmp and, more reoenw, mug
handicapped mammals Tns In<U+FB02>uence on human soclew nzs gwen Inem me sobnquel, "man‘s best mend"

High quality image works better

Dog
From Wikipedia, the free encyclopedia

This article is about the domestic dog. For related species known as "dogs", see Canidae. For other uses, see Dog (disambiguation).

”Doggie" redirects here. For the Danish artist, see Doggie (artist).
The domestic dog (Canis lupus familiaris or Canis familiaris<U+FB02>z] is a member of genus Canis (canines) that forms part of the wolf-like canids,[3] and
is the most widely abundant carnivore.[4][5][5] The dog and the extant gray wolf are sister taxa,[7][8][9] with modern wolves not closely related to the
wolves that were first domesticatedla<U+FB02>gl Since its domestication, the dog has been selectively bred over millennia for various behaviors, sensory
capabilities, and physical attributeslwl
Their long association with humans has led to dogs being uniquely attuned to human behaviorm] and are able to thrive on a starch-rich diet which
would be inadequate for other canid species.[1 2] Dogs are also the oldest domesticated animal. Dogs vary widely in shape, size and colours.[131
Dogs perform many roles for people, such as hunting, herding, pulling loads, protection, assisting police and military, companionship and, more
recently, aiding handicapped individuals. This influence on human society has given them the sobriquet, "man's best friend".