def image_file_to_string(filename,
lang=_language,
psm=_pagesegmode,
cleanup=_cleanup_scratch_flag,
graceful_errors=True):
"""Applies tesseract to filename; or, if image is incompatible and graceful_errors=True,
converts to compatible format and then applies tesseract. Fetches resulting text.
If cleanup=True, delete scratch files after operation. Parameter lang specifies used language.
If lang is empty, English is used. Page segmentation mode parameter psm is available in Tesseract 3.01.
psm values are:
0 = Orientation and script detection (OSD) only.
1 = Automatic page segmentation with OSD.
2 = Automatic page segmentation, but no OSD, or OCR
3 = Fully automatic page segmentation, but no OSD. (Default)
4 = Assume a single column of text of variable sizes.
5 = Assume a single uniform block of vertically aligned text.
6 = Assume a single uniform block of text.
7 = Treat the image as a single text line.
8 = Treat the image as a single word.
9 = Treat the image as a single word in a circle.
10 = Treat the image as a single character."""
try:
try:
call_tesseract(filename, scratch_text_name_root, lang, psm)
result = util.retrieve_result(scratch_text_name_root)
except errors.Tesser_General_Exception:
if graceful_errors:
im = Image.open(filename)
result = image_to_string(im, cleanup)
else:
raise
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return result
def image_file_to_string(filename, lang = _language, psm = _pagesegmode, cleanup = _cleanup_scratch_flag, graceful_errors=True): """Applies tesseract to filename; or, if image is incompatible and graceful_errors=True, converts to compatible format and then applies tesseract. Fetches resulting text. If cleanup=True, delete scratch files after operation. Parameter lang specifies used language. If lang is empty, English is used. Page segmentation mode parameter psm is available in Tesseract 3.01. psm values are: 0 = Orientation and script detection (OSD) only. 1 = Automatic page segmentation with OSD. 2 = Automatic page segmentation, but no OSD, or OCR 3 = Fully automatic page segmentation, but no OSD. (Default) 4 = Assume a single column of text of variable sizes. 5 = Assume a single uniform block of vertically aligned text. 6 = Assume a single uniform block of text. 7 = Treat the image as a single text line. 8 = Treat the image as a single word. 9 = Treat the image as a single word in a circle. 10 = Treat the image as a single character.""" try: try: call_tesseract(filename, scratch_text_name_root, lang, psm) result = util.retrieve_result(scratch_text_name_root) except errors.Tesser_General_Exception: if graceful_errors: im = Image.open(filename) result = image_to_string(im, cleanup) else: raise finally: if cleanup: util.perform_cleanup(scratch_image_name, scratch_text_name_root) return result
def image_to_string(im, cleanup=_cleanup_scratch_flag):
"""Converts im to file, applies tesseract, and fetches resulting text.
If cleanup=True, delete scratch files after operation."""
try:
util.image_to_scratch(im, scratch_image_name)
call_tesseract(scratch_image_name, scratch_text_name_root)
result = util.retrieve_result(scratch_text_name_root)
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return result
def image_to_string(im, cleanup=_cleanup_scratch_flag):
"""Converts im to file, applies tesseract, and fetches resulting text.
If cleanup=True, delete scratch files after operation."""
try:
util.image_to_scratch(im, scratch_image_name)
call_tesseract(scratch_image_name, scratch_text_name_root)
result = util.retrieve_result(scratch_text_name_root)
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return result
def image_file_to_string(filename, cleanup=_cleanup_scratch_flag, graceful_errors=True):
"""Applies tesseract to filename; or, if image is incompatible and graceful_errors=True,
converts to compatible format and then applies tesseract. Fetches resulting text.
If cleanup=True, delete scratch files after operation."""
try:
try:
call_tesseract(filename, scratch_text_name_root)
result = util.retrieve_result(scratch_text_name_root)
except errors.Tesser_General_Exception:
if graceful_errors:
im = Image.open(filename)
result = image_to_string(im, cleanup)
else:
raise
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return result
def image_file_to_string(filename,
cleanup=_cleanup_scratch_flag,
graceful_errors=True):
"""Applies tesseract to filename; or, if image is incompatible and graceful_errors=True,
converts to compatible format and then applies tesseract. Fetches resulting text.
If cleanup=True, delete scratch files after operation."""
try:
try:
call_tesseract(filename, scratch_text_name_root)
result = util.retrieve_result(scratch_text_name_root)
except (errors.Tesser_General_Exception):
if graceful_errors:
im = Image.open(filename)
result = image_to_string(im, cleanup)
else:
raise
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return result
