Using the cloud vision api for label detection.

[nwaughachukwuma]

It's not clear how to do label detection with google-cloud-vision. There's a complete mismatch between what's specified in this repository and what's on the docs page. If there's been a breaking change, the docs page should be clear in making it known.

Nothing in the following link works for me - https://cloud.google.com/vision/docs/libraries

Please specify how to perform label detection using cloud vision or what document I should be looking at. Thank you.

[ohmayr]

Hi @nwaughachukwuma, thanks for reaching out. I tried the sample provided in the link and it seems to work as expected.

Code:

# Imports the Google Cloud client library
from google.cloud import vision



def run_quickstart() -> vision.EntityAnnotation:
    """Provides a quick start example for Cloud Vision."""

    # Instantiates a client
    client = vision.ImageAnnotatorClient()

    # The URI of the image file to annotate
    file_uri = "gs://cloud-samples-data/vision/label/wakeupcat.jpg"

    image = vision.Image()
    image.source.image_uri = file_uri

    # Performs label detection on the image file
    response = client.label_detection(image=image)
    print("response: ", response)
    labels = response.label_annotations

    print("Labels:")
    for label in labels:
        print(label.description)

    return labels

run_quickstart()

Output:

response:  label_annotations {
  mid: "/m/01yrx"
  description: "Cat"
  score: 0.956459463
  topicality: 0.956459463
}
label_annotations {
  mid: "/m/0d4v4"
  description: "Window"
  score: 0.938840091
  topicality: 0.938840091
}
label_annotations {
  mid: "/m/0307l"
  description: "Felidae"
  score: 0.89566052
  topicality: 0.89566052
}
label_annotations {
  mid: "/m/01lrl"
  description: "Carnivore"
  score: 0.885138333
  topicality: 0.885138333
}
label_annotations {
  mid: "/m/01k9lj"
  description: "Jaw"
  score: 0.880326807
  topicality: 0.880326807
}
label_annotations {
  mid: "/m/07k6w8"
  description: "Small to medium-sized cats"
  score: 0.863107383
  topicality: 0.863107383
}
label_annotations {
  mid: "/m/0244x1"
  description: "Gesture"
  score: 0.852604866
  topicality: 0.852604866
}
label_annotations {
  mid: "/m/01l7qd"
  description: "Whiskers"
  score: 0.84995687
  topicality: 0.84995687
}
label_annotations {
  mid: "/m/031b6r"
  description: "Window blind"
  score: 0.834581673
  topicality: 0.834581673
}
label_annotations {
  mid: "/m/0276krm"
  description: "Fawn"
  score: 0.816135049
  topicality: 0.816135049
}

Labels:
Cat
Window
Felidae
Carnivore
Jaw
Small to medium-sized cats
Gesture
Whiskers
Window blind
Fawn

Feel free to reach out if you have any questions related to the Python client. For any API specific questions, kindly submit feedback on this link.