OCR_IT

library(tesseract)
library(magick)

## Linking to ImageMagick 6.9.12.98
## Enabled features: cairo, freetype, fftw, ghostscript, heic, lcms, pango, raw, rsvg, webp
## Disabled features: fontconfig, x11

library(officer)
library(pdftools)

## Using poppler version 23.08.0

library(purrr)

# obtener texto de una imagen en PNG
pdf1 <- pdf_convert("C:\\Users\\lcbor\\Downloads\\eso3.pdf",dpi = 600) %>% map(ocr)

## Converting page 1 to eso3_1.png... done!
## Converting page 2 to eso3_2.png... done!
## Converting page 3 to eso3_3.png... done!

imagen1 <- image_read("C:\\Users\\lcbor\\Documents\\eso3_1.png")
imagen2 <- image_read("C:\\Users\\lcbor\\Documents\\eso3_2.png")
imagen3 <- image_read("C:\\Users\\lcbor\\Documents\\eso3_3.png")

tesseract_download("spa")

## [1] "C:\\Users\\lcbor\\AppData\\Local\\tesseract5\\tesseract5\\tessdata/spa.traineddata"

texto1 <- ocr(imagen1, engine = tesseract("spa"))
texto2 <- ocr(imagen2, engine = tesseract("spa"))
texto3 <- ocr(imagen3, engine = tesseract("spa"))

# Guardar texto en word
doc1 <- read_docx()
doc1 <- doc1 %>% body_add_par(texto1, style = "Normal")
print(doc1,target = "pdfIT_1.docx")

doc2 <- read_docx()
doc2 <- doc2 %>% body_add_par(texto2, style = "Normal")
print(doc2,target = "pdfIT_2.docx")

doc3 <- read_docx()
doc3 <- doc3 %>% body_add_par(texto3, style = "Normal")
print(doc3,target = "pdfIT_3.docx")

# Este codigo es capaz de traducir el texto de IT de imagen a texto de forma rapida