read PNG and extract data

[ernestguevarra]

something like this:

library(magick)
#> Linking to ImageMagick 7.1.0.31
#> Enabled features: cairo, fontconfig, freetype, heic, lcms, pango, raw, rsvg, webp, x11
#> Disabled features: fftw, ghostscript
#> Using 12 threads
library(tesseract)
input <- image_read("https://i.stack.imgur.com/JxGHc.png") %>% 
  # preprocess image to make it easier to ocr
  image_convert(type = 'Grayscale') %>% 
  image_deskew() %>% 
  image_resize("2000x") %>% 
  ocr()

df <- data.table::fread(text = input)
#> Warning in data.table::fread(text = input): Detected 11 column names but the
#> data has 12 columns (i.e. invalid file). Added 1 extra default column name for
#> the first column which is guessed to be row names or an index. Use setnames()
#> afterwards if this guess is not correct, or fix the file write command that
#> created the file to create a valid file.
df
#>     V1     info    tmax ACREAGE                               GLOBALID
#>  1:  1 PRISM_tm 30.3976  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  2:  2 PRISM_tm 26.0226  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  3:  3 PRISM_tm 27.1775  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  4:  4 PRISM_tm  24,164  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  5:  5 PRISM_tm  24.458  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  6:  6 PRISM_tm  26.118  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  7:  7 PRISM_tm  27.259  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  8:  8 PRISM_tm  30.105  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>  9:  9 PRISM_tm  30.697  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 10: 10 PRISM_tm   32949  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 11: 11 PRISM_tm  32,966  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 12: 12 PRISM_tm  32.081  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 13: 13 PRISM_tm  29.847  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 14: 14 PRISM_tm  27.576  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 15: 15 PRISM_tm  24.671  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 16: 16 PRISM_tm  24.382  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 17: 17 PRISM_tm  24.382  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 18: 18 PRISM_tm  26.365  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 19: 19 PRISM_tm  29.246  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 20: 20 PRISM_tm  30.737  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 21: 21 PRISM_tm  31.658  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 22: 22 PRISM_tm  31.386  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 23: 23 PRISM_tm   32457  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 24: 24 PRISM_tm  32.093  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 25: 25 PRISM_tm  30.303  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 26: 26 PRISM_tm  26.231  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#> 27: 27 PRISM_tm  25.956  783805 {257865E5-DA82-41F8-B679-169C60B2BB4D}
#>     V1     info    tmax ACREAGE                               GLOBALID
#>     datasource variable    datatype resolutior    Date year month
#>  1:      PRISM     tmax provisional      4kmM3 2021-10 2021    10
#>  2:      PRISM     tmax provisional      4kmM3 2021-11 2021    11
#>  3:      PRISM     tmax provisional      4kmM3 2021-12 2021    12
#>  4:      PRISM     tmax      stable      4kmM3 2005-01 2005     1
#>  5:      PRISM     tmax      stable      4kmM3 2005-02 2005     2
#>  6:      PRISM     tmax      stable      4kmM3 2005-03 2005     3
#>  7:      PRISM     tmax      stable      4kmM3 2005-04 2005     4
#>  8:      PRISM     tmax      stable      4kmM3 2005-05 2005     5
#>  9:      PRISM     tmax      stable      4kmM3 2005-06 2005     6
#> 10:      PRISM     tmax      stable      4kmM3 2005-07 2005     7
#> 11:      PRISM     tmax      stable      4kmM3 2005-08 2005     8
#> 12:      PRISM     tmax      stable      4kmM3 2005-09 2005     9
#> 13:      PRISM     tmax      stable      4kmM3 2005-10 2005    10
#> 14:      PRISM     tmax      stable      4kmM3 2005-11 2005    11
#> 15:      PRISM     tmax      stable      4kmM3 2005-12 2005    12
#> 16:      PRISM     tmax      stable      4kmM3 2006-01 2006     1
#> 17:      PRISM     tmax      stable      4kmM3 2006-02 2006     2
#> 18:      PRISM     tmax      stable      4kmM3 2006-03 2006     3
#> 19:      PRISM     tmax      stable      4kmM3 2006-04 2006     4
#> 20:      PRISM     tmax      stable      4kmM3 2006-05 2006     5
#> 21:      PRISM     tmax      stable      4kmM3 2006-06 2006     6
#> 22:      PRISM     tmax      stable      4kmM3 2006-07 2006     7
#> 23:      PRISM     tmax      stable      4kmM3 2006-08 2006     8
#> 24:      PRISM     tmax      stable      4kmM3 2006-09 2006     9
#> 25:      PRISM     tmax      stable      4kmM3 2006-10 2006    10
#> 26:      PRISM     tmax      stable      4kmM3 2006-11 2006    11
#> 27:      PRISM     tmax      stable      4kmM3 2006-12 2006    12
#>     datasource variable    datatype resolutior    Date year month

from https://stackoverflow.com/questions/73238598/r-extract-text-from-image-and-export-it-as-a-csv