pytesser是谷歌OCR開源項目的一個模塊，在python中導入這個模塊即可將圖片中的文字轉換成文本。
pytesser 調用了 tesseract。在python中調用pytesser模塊，pytesser又用tesseract識別圖片中的文字。
下面是整個過程的實現步驟：
1、首先要在code.google.com下載pytesser。https://code.google.com/p/pytesser/downloads/detail?name=pytesser_v0.0.1.zip
這個是免安裝的，可以放在python安裝文件夾的\Lib\site-packages\ 下直接使用
pytesser里包含了tesseract.exe和英語的數據包（默認只識別英文），還有一些示例圖片，所以解壓縮后即可使用。
可通過以下代碼測試：
>>> from pytesser import *
>>> image = Image.open('fnord.tif') # Open image object using PIL
>>> print image_to_string(image) # Run tesseract.exe on image
fnord
>>> print image_file_to_string('fnord.tif')
fnord
from pytesser import *
#im = Image.open('fnord.tif')
#im = Image.open('phototest.tif')
#im = Image.open('eurotext.tif')
im = Image.open('fonts_test.png')
text = image_to_string(im)
print text
注：該模塊需要PIL庫的支持。
2、解決識別率低的問題
可以增強圖片的顯示效果，或者將其轉換為黑白的，這樣可以使其識別率提升不少：
enhancer = ImageEnhance.Contrast(image1) image2 = enhancer.enhance(4)
可以再對image2調用 image_to_string識別
3、識別其他語言
tesseract是一個命令行下運行的程序，參數如下：
tesseract imagename outbase [-l lang] [-psm N] [configfile...]
imagename是輸入的image的名字
outbase是輸出的文本的名字，默認為outbase.txt
-l lang 是定義要識別的的語言，默認為英文
通過以下步驟可以識別其他語言：
（1）、下載其他語言數據包：
將語言包放入pytesser的tessdata文件夾下
接下來修改pytesser.py的參數，下面是一個例子：
"""OCR in Python using the Tesseract engine from Google
http://code.google.com/p/pytesser/
by Michael J.T. O'Kelly
V 0.0.2, 5/26/08"""
import Image
import subprocess
import os
import StringIO
import util
import errors
tesseract_exe_name = 'dlltest' # Name of executable to be called at command line
scratch_image_name = "temp.bmp" # This file must be .bmp or other Tesseract-compatible format
scratch_text_name_root = "temp" # Leave out the .txt extension
_cleanup_scratch_flag = True # Temporary files cleaned up after OCR operation
_language = "" # Tesseract uses English if language is not given
_pagesegmode = "" # Tesseract uses fully automatic page segmentation if psm is not given (psm is available in v3.01)
_working_dir = os.getcwd()
def call_tesseract(input_filename, output_filename, language, pagesegmode):
"""Calls external tesseract.exe on input file (restrictions on types),
outputting output_filename+'txt'"""
current_dir = os.getcwd()
error_stream = StringIO.StringIO()
try:
os.chdir(_working_dir)
args = [tesseract_exe_name, input_filename, output_filename]
if len(language) > 0:
args.append("-l")
args.append(language)
if len(str(pagesegmode)) > 0:
args.append("-psm")
args.append(str(pagesegmode))
try:
proc = subprocess.Popen(args)
except (TypeError, AttributeError):
proc = subprocess.Popen(args, shell=True)
retcode = proc.wait()
if retcode!=0:
error_text = error_stream.getvalue()
errors.check_for_errors(error_stream_text = error_text)
finally: # Guarantee that we return to the original directory
error_stream.close()
os.chdir(current_dir)
def image_to_string(im, lang = _language, psm = _pagesegmode, 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, lang, psm)
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, 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
if __name__=='__main__':
im = Image.open('phototest.tif')
text = image_to_string(im, cleanup=False)
print text
text = image_to_string(im, psm=2, cleanup=False)
print text
try:
text = image_file_to_string('fnord.tif', graceful_errors=False)
except errors.Tesser_General_Exception, value:
print "fnord.tif is incompatible filetype. Try graceful_errors=True"
#print value
text = image_file_to_string('fnord.tif', graceful_errors=True, cleanup=False)
print "fnord.tif contents:", text
text = image_file_to_string('fonts_test.png', graceful_errors=True)
print text
text = image_file_to_string('fonts_test.png', lang="eng", psm=4, graceful_errors=True)
print text
這個是source里面提供的，其實若只要識別其他語言只要添加一個language參數就行了，下面是我的例子：
"""OCR in Python using the Tesseract engine from Google
http://code.google.com/p/pytesser/
by Michael J.T. O'Kelly
V 0.0.1, 3/10/07"""
import Image
import subprocess
import util
import errors
tesseract_exe_name = 'tesseract' # Name of executable to be called at command line
scratch_image_name = "temp.bmp" # This file must be .bmp or other Tesseract-compatible format
scratch_text_name_root = "temp" # Leave out the .txt extension
cleanup_scratch_flag = True # Temporary files cleaned up after OCR operation
def call_tesseract(input_filename, output_filename, language):
"""Calls external tesseract.exe on input file (restrictions on types),
outputting output_filename+'txt'"""
args = [tesseract_exe_name, input_filename, output_filename, "-l", language]
proc = subprocess.Popen(args)
retcode = proc.wait()
if retcode!=0:
errors.check_for_errors()
def image_to_string(im, cleanup = cleanup_scratch_flag, language = "eng"):
"""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,language)
text = util.retrieve_text(scratch_text_name_root)
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return text
def image_file_to_string(filename, cleanup = cleanup_scratch_flag, graceful_errors=True, language = "eng"):
"""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, language)
text = util.retrieve_text(scratch_text_name_root)
except errors.Tesser_General_Exception:
if graceful_errors:
im = Image.open(filename)
text = image_to_string(im, cleanup)
else:
raise
finally:
if cleanup:
util.perform_cleanup(scratch_image_name, scratch_text_name_root)
return text
if __name__=='__main__':
im = Image.open('phototest.tif')
text = image_to_string(im)
print text
try:
text = image_file_to_string('fnord.tif', graceful_errors=False)
except errors.Tesser_General_Exception, value:
print "fnord.tif is incompatible filetype. Try graceful_errors=True"
print value
text = image_file_to_string('fnord.tif', graceful_errors=True)
print "fnord.tif contents:", text
text = image_file_to_string('fonts_test.png', graceful_errors=True)
print text
在調用image_to_string函數時，只要加上相應的language參數就可以了，如簡體中文最后一個參數即為 chi_sim， 繁體中文chi_tra,
也就是下載的語言包的 XXX.traineddata 文件的名字XXX，如下載的中文包是 chi_sim.traineddata， 參數就是chi_sim :
text = image_to_string(self.im, language = 'chi_sim')
至此，圖片識別就完成了。
額外附加一句：有可能中文識別出來了，但是亂碼，需要相應地將text轉換為你所用的中文編碼方式，如：
text.decode("utf8")就可以了