Update docs to describe ocr_image defaults

The example scripts now work with the included tessdata models.

README.org

@@ -49,7 +49,7 @@ PDF=$1
 python -m table_ocr.pdf_to_images $PDF | grep .png > /tmp/pdf-images.txt
 cat /tmp/pdf-images.txt | xargs -I{} python -m table_ocr.extract_tables {}  | grep table > /tmp/extracted-tables.txt
 cat /tmp/extracted-tables.txt | xargs -I{} python -m table_ocr.extract_cells {} | grep cells > /tmp/extracted-cells.txt
-cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {} --psm 7 -l table-ocr
+cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {}
 
 for image in $(cat /tmp/extracted-tables.txt); do
     dir=$(dirname $image)
@@ -57,6 +57,7 @@ for image in $(cat /tmp/extracted-tables.txt); do
 done
 #+END_SRC
 
+
 The package was written in a [[https://en.wikipedia.org/wiki/Literate_programming][literate programming]] style. The source code at
 [[https://eihli.github.io/image-table-ocr/pdf_table_extraction_and_ocr.html]] is
 meant to act as the documentation and reference material.

ocr_tables

@@ -5,8 +5,7 @@ PDF=$1
 python -m table_ocr.pdf_to_images $PDF | grep .png > /tmp/pdf-images.txt
 cat /tmp/pdf-images.txt | xargs -I{} python -m table_ocr.extract_tables {}  | grep table > /tmp/extracted-tables.txt
 cat /tmp/extracted-tables.txt | xargs -I{} python -m table_ocr.extract_cells {} | grep cells > /tmp/extracted-cells.txt
-cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {} --psm 7 -l table-ocr
+cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {}
-
 for image in $(cat /tmp/extracted-tables.txt); do
     dir=$(dirname $image)
     python -m table_ocr.ocr_to_csv $(find $dir/cells -name "*.txt")

pdf_table_extraction_and_ocr.org

@@ -97,14 +97,15 @@ PDF=$1
 python -m table_ocr.pdf_to_images $PDF | grep .png > /tmp/pdf-images.txt
 cat /tmp/pdf-images.txt | xargs -I{} python -m table_ocr.extract_tables {}  | grep table > /tmp/extracted-tables.txt
 cat /tmp/extracted-tables.txt | xargs -I{} python -m table_ocr.extract_cells {} | grep cells > /tmp/extracted-cells.txt
-cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {} --psm 7 -l table-ocr
+cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {}
-
 for image in $(cat /tmp/extracted-tables.txt); do
     dir=$(dirname $image)
     python -m table_ocr.ocr_to_csv $(find $dir/cells -name "*.txt")
 done
 #+END_SRC
 
+Any extra args you pass after the image path to ~python -m table_ocr.ocr_image~ will be passed directly to tesseract as options. If you don't pass anything, reasonable english defaults are used.
+
 ** Possible improvements
 
 Detect text with the stroke-width-transform alogoritm. https://zablo.net/blog/post/stroke-width-transform-swt-python/index.html
@@ -199,7 +200,7 @@ def preprocess_img(filepath, tess_params=None):
     like mogrify to rotate.
 
     Uses tesseract to detect rotation.
-   
+
     Orientation and script detection is only available for legacy tesseract
     (--oem 0). Some versions of tesseract will segfault if you let it run OSD
     with the default oem (3).