利用pytesser模块实现图片文字识别

Pytesser——OCR in Python using the Tesseract engine from Google

pytesser是谷歌OCR开源项目的一个模块，在python中导入这个模块即可将图片中的文字转换成文本。

链接： https://code.google.com/p/pytesser/

pytesser  调用了  tesseract。在python中调用pytesser模块，pytesser又用tesseract识别图片中的文字。

下面是整个过程的实现步骤：

1、首先要在code.google.com下载pytesser。https://code.google.com/p/pytesser/downloads/detail?name=pytesser_v0.0.1.zip

这个是免安装的，可以放在python安装文件夹的\Lib\site-packages\  下直接使用

pytesser里包含了tesseract.exe和英语的数据包（默认只识别英文），还有一些示例图片，所以解压缩后即可使用。

可通过以下代码测试：

 >>> 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

 "code" class="python">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：该模块需要PIL库的支持。

2、解决识别率低的问题

可以增强图片的显示效果，或者将其转换为黑白的，这样可以使其识别率提升不少：

 enhancer = ImageEnhance.Contrast(image1)
 image2 = enhancer.enhance(4)

可以再对image2调用 image_to_string识别

3、识别其他语言

tesseract是一个命令行下运行的程序，参数如下：

tesseract  imagename outbase [-l  lang]  [-psm N]  [configfile...]

imagename是输入的image的名字

outbase是输出的文本的名字，默认为outbase.txt

-l  lang  是定义要识别的的语言，默认为英文

详见 http://tesseract-ocr.googlecode.com/svn-history/r725/trunk/doc/tesseract.1.html

通过以下步骤可以识别其他语言：

（1）、下载其他语言数据包：

https://code.google.com/p/tesseract-ocr/downloads/list

将语言包放入pytesser的tessdata文件夹下

接下来修改pytesser.py的参数，下面是一个例子：

 """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

这个是source里面提供的，其实若只要识别其他语言只要添加一个language参数就行了，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

在调用image_to_string函数时，只要加上相应的language参数就可以了，如简体中文最后一个参数即为 chi_sim， 繁体中文chi_tra,

也就是下载的语言包的 XXX.traineddata 文件的名字XXX，如下载的中文包是 chi_sim.traineddata， 参数就是chi_sim :

 text = image_to_string(self.im, language = 'chi_sim')

至此，图片识别就完成了。

额外附加一句：有可能中文识别出来了，但是乱码，需要相应地将text转换为你所用的中文编码方式，如：

text.decode("utf8")就可以了