计算机视觉API V2错误:识别文本 [英] Error with computer vision API V2: recognize text

问题描述

我正在尝试使用Microsoft识别文本，计算机视觉API将收据图片转换为文本.但是我没有使其正常运行，而是获得了响应代码202，该响应代码 表示 请求 已收到但尚未收到 此处 是我在python中使用的代码:

I am trying to use Microsoft recognize text, computer vision API to convert a receipt picture to text. But I dont get it run properly and instead I get response code 202, which indicates that the request has been received but not yet acted upon. Here is the code I use in python:

import requests

subscription_key ="mySubscriptionKey" 断言subscription_key #将我的图片读入二进制版本: image_path ="images/DSC_0127.JPG"； image_data = open(image_path，"rb").read() vision_base_url ="https://westeurope.api.cognitive.microsoft.com/vision/v2.0/" #添加识别文本API: api_url = vision_base_url +"recognizeText" 标头= {'Ocp-Apim-Subscription-Key':subscription_key， 'Content-Type':'application/octet-stream'} params = {'mode':'Printed'} 响应= request.post( api_url，标头=标头，参数=参数，数据=图像数据) response.raise_for_status() 分析= response.json()

subscription_key = "mySubscriptionKey" assert subscription_key # read my image into binary version: image_path = "images/DSC_0127.JPG" image_data = open(image_path, "rb").read() vision_base_url = "https://westeurope.api.cognitive.microsoft.com/vision/v2.0/" # add recognizeText API: api_url = vision_base_url + "recognizeText" headers = {'Ocp-Apim-Subscription-Key': subscription_key, 'Content-Type': 'application/octet-stream'} params = {'mode': 'Printed'} response = requests.post( api_url, headers=headers, params=params, data=image_data) response.raise_for_status() analysis = response.json()

任何帮助将不胜感激.

推荐答案

您好Rozita，

这里也有类似的问题报道:

https://stackoverflow.com/questions/50213090/computer-vision-api-v1-0-recognize-handwriting-text-returns-empty-response

请查看答案，看看是否有帮助.如果没有，请告知我们，我们可以继续进行对话.

Hi Rozita,

There's a similar issue reported here :

https://stackoverflow.com/questions/50213090/computer-vision-api-v1-0-recognize-handwritten-text-returns-empty-response

Please have a look at the answer and see if it helps. If not, please let us know, we can gladly continue the dialogue.

这篇关于计算机视觉API V2错误:识别文本的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！