基于Python的OCR实现示例

import pytesseract
from PIL import Image
img = Image.open('./testImages/test01.jpg')
pytesseract.pytesseract.tesseract_cmd = 'C:/Program Files (x86)/Tesseract-OCR/tesseract.exe'
s = pytesseract.image_to_string(img, lang='chi_sim') #不加lang参数的话，默认进行英文识别
print(s)

from aip import AipOcr
APP_ID = '00000000'
API_KEY = '00000000000000000000'
SECRET_KEY = '00000000000000000000'
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
 
def get_file_content(filePath):
  with open(filePath, 'rb') as fp:
    return fp.read()
 
def image2text(fileName):
  image = get_file_content(fileName)
  dic_result = client.basicGeneral(image)
  res = dic_result['words_result']
  result = ''
  for m in res:
    result = result + str(m['words'])
  return result
 
getresult = image2text('./test01.jpg')
print(getresult)

import pytesseract
import requests
from PIL import Image
from PIL import ImageFilter
from StringIO import StringIO
from werkzeug.utils import secure_filename
from gevent import monkey
from gevent.pywsgi import WSGIServer
monkey.patch_all()
from flask import Flask,render_template,jsonify,request,send_from_directory
import time
import os
import base64
import random


app = Flask(__name__)
UPLOAD_FOLDER='upload'
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
basedir = os.path.abspath(os.path.dirname(__file__))
ALLOWED_EXTENSIONS = set(['png','jpg','JPG','PNG'])

def allowed_file(filename):
  return '.' in filename and filename.rsplit('.',1)[1] in ALLOWED_EXTENSIONS

@app.route('/',methods=['GET'],strict_slashes=False)
def indexpage():
  return render_template('index.html')

@app.route('/',methods=['POST'],strict_slashes=False)
def api_upload():
  log = open("error.log","w+")
  file_dir = os.path.join(basedir, app.config['UPLOAD_FOLDER'])
  if not os.path.exists(file_dir):
    os.makedirs(file_dir)
  print request.headers
  print >> log, request.headers
  f = request.files['file']
  postLang = request.form.get("lang", type=str) 

  log.close()

  if f and allowed_file(f.filename):
    fname = secure_filename(f.filename)
    ext = fname.rsplit('.',1)[1]
    unix_time = int(time.time())
    new_filename = str( random.randrange(0, 10001, 2))+str(unix_time)+'.'+ext
    f.save(os.path.join(file_dir,new_filename))
    if cmp(postLang, "chi_sim"):
      strboxs = pytesseract.image_to_boxes(Image.open("/var/OCRhtml/upload/" + new_filename), lang="chi_sim")
      strdata = pytesseract.image_to_string(Image.open("/var/OCRhtml/upload/" + new_filename), lang="chi_sim")
      print "Chinese"
    else:
      strboxs = pytesseract.image_to_boxes(Image.open("/var/OCRhtml/upload/"+new_filename))
      strdata = pytesseract.image_to_string(Image.open("/var/OCRhtml/upload/"+new_filename))
    return jsonify({"errno":0, "msg":"succeed ","data":strdata,"info":strboxs})
  else:
    return jsonify({"errno":1001, "errmsg":u"failed"})

if __name__ == '__main__':
  http_server = WSGIServer(('', 80), app)
  http_server.serve_forever()