update20140518

This commit is contained in:
stubbfel
2014-05-18 21:21:44 +02:00
parent c66a4b8fa0
commit 8abf4c8fb2
3 changed files with 16 additions and 5 deletions

View File

@@ -1,12 +1,12 @@
#!/bin/bash
for FILE in "$@"
do
pdfseparate "$FILE" pdf2txtTemp-%d.pdf
for i in pdf2txtTemp-*.pdf
pdftoppm $FILE pdf2txtTemp
for i in pdf2txtTemp-*.ppm
do
convert -monochrome -normalize -density 300 $i $i.png
tesseract $i.png $i -l eng+deu
ppm2tiff $i $i.tiff
tesseract $i.tiff $i -l eng+deu
done
cat pdf2txtTemp-*.pdf.txt > "$FILE".txt
cat pdf2txtTemp-*.ppm.txt > "$FILE".txt
rm pdf2txtTemp-*.*
done