[PYTHON] Extract characters from images using docomo's character recognition API

Thing you want to do

I want to extract characters from an image using docomo's API.

** Addendum (2016/02/16) ** The program has been uploaded to GitHub. → source

Advance preparation

--Register with docomo Developer support to get the API key.

• docomo Developer support --Prepare the image file you want to recognize (JPEG format) --Refer to the reference for details -Reference

Image file to recognize (test.jpg)

Development environment

--python 2.7 series

program

characterRecognition.py

#coding: utf-8
from poster.encode import multipart_encode
from poster.streaminghttp import register_openers
import urllib2
import json
import time 
import urllib
import re
import sys

#Throw image data and get image ID in json format(Scene image recognition request)
def getImageID(fname):
    register_openers()
    url = 'https://api.apigw.smt.docomo.ne.jp/characterRecognition/v1/document?APIKEY=(Please enter the API key)'
    
    f = open(fname, 'r')

    datagen, headers = multipart_encode({"image": f, 'lang': 'jpn'})
    request = urllib2.Request(url,datagen, headers)
    response = urllib2.urlopen(request)
    
    res_dat = response.read()
    return json.loads(res_dat)['job']['@id'] #Returns the ID of the image

#Extract only the word from the acquired json.
def makeWordList(result):
    
    word_list = []
    count  = int(result['lines']['@count'])

    for i in range(count):
        word = result['lines']['line'][i]['@text']
        word_list.append(word)

    return word_list

#Scene image recognition result acquisition
def getWordList(img_id):

    register_openers()
    url = 'https://api.apigw.smt.docomo.ne.jp/characterRecognition/v1/document/' + img_id + '?APIKEY=(Please enter the API key)'
    
    request = urllib2.Request(url)
    
    recog_result = {}
    for i in range(5):
        response = urllib2.urlopen(request)
        res_dat = response.read()
        
        recog_result = json.loads(res_dat)
        
        status = recog_result['job']['@status']
        
        if status == 'queue':
            print 'Accepting...'
        elif status == 'process':
            print 'Recognizing...'
        elif status == 'success':
            print 'Successful recognition' #, recog_result
            word_list = makeWordList(recog_result)
            return word_list
        elif status == 'failure':
            print 'Recognition failure'
            return None

        time.sleep(3) #wait a little



if __name__ == '__main__':
    
    #Get image ID
    img_id = getImageID(sys.argv[1])
    
    #Get word list
    word_list = getWordList(img_id)
    
    #Display the recognized character string
    for word in word_list:
        print word

Execution result

>python characterRecognition.py test.jpg
Recognizing...
Successful recognition
Character recognition test

Supplement (example of acquired json)

{
  "job": {
    "@status": "success",
    "@id": "(Image ID)", #Image ID
    "@queue-time": "2016/02/13 17:03:07"
  },
  "lines": {
    "line": [
      {
        "@text": "\u6587\u5b57\u8a8d\u8b58\u306e\u30c6\u30b9\u30c8", #Recognized string
        "shape": {
          "@count": "4",
          "point": [       #Coordinates on the image of the text(Upper left, lower left, lower right, upper right)
            {
              "@x": "35",
              "@y": "33"
            },
            {
              "@x": "35",
              "@y": "67"
            },
            {
              "@x": "293",
              "@y": "67"
            },
            {
              "@x": "293",
              "@y": "33"
            }
          ]
        }
      }
    ],
    "@count": "1"
  },
  "message": null
}

Afterword

For the time being, I wrote it for a memo. If you would like to know more, please leave a comment.