Question

如果我只想从磁盘处理图像以从中读取文本并将其存储在文本文件中，该怎么办？因为它适用于json和数据。我想只处理数据。怎么做？

from __future__ import print_function
import time 
import requests
import cv2
import operator
import numpy as np

# Import library to display results
import matplotlib.pyplot as plt
%matplotlib inline 


_url = 'https://api.projectoxford.ai/vision/v1/analyses'
_key = 'd784ea882edd4feaa373dc5a80fa87e8'
_maxNumRetries = 10

def processRequest( json, data, headers, params ):

    """
    Helper function to process the request to Project Oxford

    Parameters:
    json: Used when processing images from its URL. See API Documentation
    data: Used when processing image read from disk. See API Documentation
    headers: Used to pass the key information and the data type request
    """

    retries = 0
    result = None

    while True:

        response = requests.request( 'post', _url, json = json, data = data, headers = headers, params = params )

        if response.status_code == 429: 

            print( "Message: %s" % ( response.json()['error']['message'] ) )

            if retries <= _maxNumRetries: 
                time.sleep(1) 
                retries += 1
                continue
            else: 
                print( 'Error: failed after retrying!' )
                break

        elif response.status_code == 200 or response.status_code == 201:

            if 'content-length' in response.headers and int(response.headers['content-length']) == 0: 
                result = None 
            elif 'content-type' in response.headers and isinstance(response.headers['content-type'], str): 
                if 'application/json' in response.headers['content-type'].lower(): 
                    result = response.json() if response.content else None 
                elif 'image' in response.headers['content-type'].lower(): 
                    result = response.content
        else:
            print( "Error code: %d" % ( response.status_code ) )
            print( "Message: %s" % ( response.json()['error']['message'] ) )

        break

    return result

def renderResultOnImage( result, img ):

    """Display the obtained results onto the input image"""

    R = int(result['color']['accentColor'][:2],16)
    G = int(result['color']['accentColor'][2:4],16)
    B = int(result['color']['accentColor'][4:],16)

    cv2.rectangle( img,(0,0), (img.shape[1], img.shape[0]), color = (R,G,B), thickness = 25 )

    if 'categories' in result:
        categoryName = sorted(result['categories'], key=lambda x: x['score'])[0]['name']
        cv2.putText( img, categoryName, (30,70), cv2.FONT_HERSHEY_SIMPLEX, 2, (255,0,0), 3 )


pathToFileInDisk = r'test.jpg'
with open( pathToFileInDisk, 'rb' ) as f:
    data = f.read()

# Computer Vision parameters
params = { 'visualFeatures' : 'Color,Categories'} 

headers = dict()
headers['Ocp-Apim-Subscription-Key'] = _key
headers['Content-Type'] = 'application/octet-stream'

json = None

result = processRequest( json, data, headers, params )

if result is not None:
    # Load the original image, fetched from the URL
    data8uint = np.fromstring( data, np.uint8 ) # Convert string to an unsigned int array
    img = cv2.cvtColor( cv2.imdecode( data8uint, cv2.IMREAD_COLOR ), cv2.COLOR_BGR2RGB )

    renderResultOnImage( result, img )

    ig, ax = plt.subplots(figsize=(15, 20))
    ax.imshow( img )

它在％matplot内联显示sytax错误

Answer 1

我收集你从某个地方复制了你的Python代码，并且有很多问题：

您的语法错误源于％matplotlib是iPython的有效语法，而不是纯Python。
根据您的问题描述，IIUC，您不需要任何绘图代码，因此您可以删除matplotlib（以及cv2和numpy，就此而言）。
您的API网址错误：您需要https://api.projectoxford.ai/vision/v1.0/ocr。
您想要的代码基本上就是这样：

import json
import requests
import urllib

headers = {
    # Request headers
    'Content-Type': 'application/json',
    'Ocp-Apim-Subscription-Key': 'YOUR_KEY_HERE',
}

params = urllib.urlencode({
    # Request parameters
    'language': 'unk',
    'detectOrientation ': 'true',
})

body = {"url":"YOUR_URL_HERE"}
response = requests.post("https://api.projectoxford.ai/vision/v1.0/ocr?%s" % params, json=body, headers=headers)
result = response.json()
for region in result['regions']:
  for line in region['lines']:
    for word in line['words']:
      print word['text']

获取有关API page上的响应JSON的更多详细信息，例如，如果您希望以不同方式排列文本。
您忘了编辑API密钥，因此您可能希望通过订阅page生成新密钥。

OCR使用微软认知

1 个答案: