Questions tagged [google-cloud-vision]

Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API.

Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API. It quickly classifies images into thousands of categories (e.g., "sailboat", "lion", "Eiffel Tower"), detects individual objects and faces within images, and finds and reads printed words contained within images.

You can build metadata on your image catalog, moderate offensive content, or enable new marketing scenarios through image sentiment analysis. Analyze images uploaded in the request, and in upcoming releases, integrate with your image storage on Google Cloud Storage. Documentation

770 questions
26
votes
2 answers

Is there a full list of potential labels that Google's Vision API will return?

I've been testing out Google's Vision API to attach labels to different images. For a given image, I'll get back something like this: "google_labels": { "responses": [{ "labelAnnotations": [{ "score":…
Hillary Sanders
  • 4,865
  • 7
  • 27
  • 46
21
votes
1 answer

Get Lines and Paragraphs, not symbols from Google Vision API OCR on PDF

I am attempting to use the now supported PDF/TIFF Document Text Detection from the Google Cloud Vision API. Using their example code I am able to submit a PDF and receive back a JSON object with the extracted text. My issue is that the JSON file…
meepl
  • 8,533
  • 16
  • 54
  • 88
17
votes
2 answers

Google Cloud Vision - Numbers and Numerals OCR

I've been trying to implement an OCR program with Python that reads numbers with a specific format, XXX-XXX. I used Google's Cloud Vision API Text Recognition, but the results were unreliable. Out of 30 high-contrast 1280 x 1024 bmp images, only a…
16
votes
6 answers

Get correct image orientation by Google Cloud Vision api (TEXT_DETECTION)

I tried Google Cloud Vision api (TEXT_DETECTION) on 90 degrees rotated image. It still can return recognized text correctly. (see image below) That means the engine can recognize text even the image is 90, 180, 270 degrees rotated. However the…
Jack Fan
  • 1,837
  • 3
  • 15
  • 24
16
votes
4 answers

API Key not valid error when trying to access Google cloud vision api

I am trying to test out the vision API and have uploaded some images to Google cloud storage and have created a browser app that requests the cloud api to process them. I have a client_id file that I downloaded from the Google developers console.…
Roaders
  • 3,916
  • 4
  • 39
  • 65
15
votes
1 answer

Google Vision API does not recognize single digits

I have a project that make use of Google Vision API DOCUMENT_TEXT_DETECTION in order to extract text from document images. Often the API has troubles in recognizing single digits, as you can see in this image: I suppose that the problem could be…
14
votes
8 answers

"We can not access the URL currently."

I call google api when the return of "We can not access the URL currently." But the resources must exist and can be accessed. https://vision.googleapis.com/v1/images:annotate request content: { "requests": [ { "image": { …
wei193
  • 141
  • 1
  • 3
13
votes
5 answers

Can google vision API accept external image URL?

I am reading documentation on vision API request schema. In image source, I only see option of using url of GCS image paths. Is it possible to use external image url like http://example.com/images/image01.jpg ?
Ashish Jain
  • 279
  • 1
  • 4
  • 13
12
votes
5 answers

Google Cloud Vision API Permission Denied

I was trying to run the sample app, found here Github Sample, I have created a certificate and created a API Key and applied as instructed. But when I upload the Image I am getting this Exception. I dont know where I have made a mistake. Have I…
Amalan Dhananjayan
  • 2,167
  • 1
  • 31
  • 47
11
votes
3 answers

How to install google.cloud with Python pip?

I am relatively new to Python and I am stuck on something which is probably relatively easy to resolve. I have installed the following packages: pip install --upgrade google-api-python-client pip install --upgrade google-cloud pip install --upgrade…
Bob van Luijt
  • 6,076
  • 9
  • 46
  • 85
10
votes
6 answers

How to upload an image to Google Cloud Storage from an image url in Node?

Given an image url, how can I upload that image to Google Cloud Storage for image processing using Node.js?
9
votes
2 answers

Google cloud vision not accepting base64 encoded images python

I'm having a problem with base64 encoded images sent to Google Cloud Vision. Funny thing is that if I send the image via URI, it works fine, so I suspect there is something wrong the way I'm encoding. Here's the deal: from google.cloud import…
AlejandroVK
  • 6,905
  • 11
  • 43
  • 68
9
votes
1 answer

Using the Google Cloud Vision API with a simple API key

I am using the Google Cloud Vision Java API client documented here: https://cloud.google.com/vision/docs/reference/libraries. The following quickstart code works fine if I use the implicit default credentials by setting the…
mac01021
  • 601
  • 4
  • 12
9
votes
1 answer

Google Cloud Vision API - How to enable a service account

I am trying to get my head round GoogleVision API Java library. I have created a service account, downloaded the json and set this environment variable. GOOGLE_APPLICATION_CREDENTIALS=C:\GoogleAPI\keys\translate-41428d4d1ec6.json I have set…
smackenzie
  • 2,476
  • 3
  • 29
  • 79
9
votes
1 answer

Incomplete coordinate values for Google Vision OCR

I have a script that is iterating through images of different forms. When parsing the Google Vision Text detection response, I use the XY coordinates in the 'boundingPoly' for each text item to specifically look for data in different parts of the…
crld
  • 357
  • 3
  • 8
1
2 3
51 52