I am performing some OCR operation with tesseract. I have written a simple python wrapper for that. The problem is I am getting unwanted line gaps between sentences in the end text file, which I need to remove programmatically. for example:
1 tbsp peanut or corn oil, plus a little
extra for Cooking the scallops
2 tbsp bottled mild or medium Thai
green curry paste
2 tbsp water
2 tsp light soy sauce
Please note some line gaps--which I need to remove. Please share some tips if you experienced similar problems. Thank you.
Here is the wrapper:
from PIL import Image
import subprocess
import os
from wand.image import Image
import markdown2
from textblob import TextBlob
import util
import errors
tesseract_exe = "tesseract" # Name of executable to be called at command line
scratch_text_name_root = "temp" # Leave out the .txt extension
cleanup_scratch_flag = True # Temporary files cleaned up after OCR operation
pagesegmode = "-psm 0"
def call_tesseract(input_file, output_file):
args = [tesseract_exe, input_file, output_file, pagesegmode]
proc = subprocess.Popen(args)
retcode = proc.wait()
if retcode !=0:
errors.check_for_errors()
def retrieve_text(scratch_text_name_root):
inf = file(scratch_text_name_root + '.txt')
text = inf.read()
inf.close()
return text
def write_to_file(filename, string):
File = open(filename, 'w')
File.write(string)
File.close()
def image_to_string(filename):
try:
call_tesseract(filename, scratch_text_name_root)
text = retrieve_text(scratch_text_name_root)
finally:
try:
os.remove(scratch_text_name_root)
except OSError:
pass
return text
filename = "book/0001.bin.png"
text = image_to_string(filename)
print "writing to file"
write_to_file("0002.bin.txt", text)