vision - 谷歌视觉 API 标签检测

Question

在google vision api label detection中，不知道物体在哪里？任何选择或想法？我在示例中尝试过，然后响应 json 不包括对象位置！

Answer 1

try this
import io
from google.cloud import vision
import argparse
import base64
import picamera
import json
import os
import picamera
import sys

from googleapiclient import discovery
from oauth2client.client import GoogleCredentials

    os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "provide here the json key path"
    camera = picamera.PiCamera()


    camera.capture('pic1.jpg')
    credentials = GoogleCredentials.get_application_default()
    service = discovery.build('vision', 'v1', credentials=credentials)

    vision_client=vision.Client()
    file_name='pic1.jpg'

    with io.open(file_name,'rb') as image_file:
        content=image_file.read()
        image=vision_client.image(content=content)


    labels = image.detect_labels()

    for label in labels:
        print(label.description)

`