Google Cloud Vision


Google Cloud Vision with App Inventor



About Extension:

A non-visible component for Google Cloud Vision that allows developers to easily integrate vision detection features within applications, including image labeling, face and landmark detection, optical character recognition (OCR), and tagging of explicit content.

Requirements:

  1. Google Cloud account with enabled CLOUD VISION API.
  2. Google Cloud CREDENTIAL API key.

Blocks:

Error Occurred


Event raised when error occurred.

Handwriting Detected


Event raised when hand writing text detected from image.

Logo Detected


Event raised when logo detected.

Text Detected


Detect and extract text from image using optical character recognition (OCR).

Detect Hand Writing


Detect and extract hand writing from image using optical character recognition (OCR).

Detect Logo

component_method(1)
Detects popular product logos within an image.

Detect Text

component_method(2)
Detect and extract text from image using optical character recognition (OCR).

API Key

component_set_get


Your Google Cloud credential API key.

Download Link

GoogleCloudVision.aix (14.9 KB)

12 Likes

Remember Google Cloud Vision is free for the first 1000 calls every month.

@Peter thank you for this information, actually I also didn't know about that.

This extension is just fun time activity, we can add more cloud vision functionality also.

You can have 1000 label detection, 1000 text detection, 1000 logo detection, etc for free every month. So for testing this should be sufficient.

3 Likes

BTW, what is Google Cloud Vision ? :sweat_smile:
Please explain in simple words.

why not look it up yourself:

1 Like

Hi is anybody in this group already implemented it?

I am looking for a sample code, please help.

hello, do you have any example how to use this extension. i try it and didn't work

did u make it ?

It works for me but for the first API call only. For the next one, I have to regenerate an API key and restart the application

Thank you so much for this extension, is working really good. Could be possible to add another block for detecting objects in the image? would be really usefull, thanks!

Thanks for making this extension. I'm trying to use this for a "image classification" app where we can post an image and get some facts (labels) about the image etc. Can I use this ? would be nice to have a sample code . thanks

Is there any aia file

First of first, you need to get a API key.

Please share sample code hiding API key

I did not use this extension, but it only has several blocks:

When Screen.Initialized
set GCV.APIkey to xxxx

When button.Clicked
call GCV.DetectText image (your image url)

When GCV.TextDetected
set label.Text to text.