Skip to main content
Filter by
Sorted by
Tagged with
0 votes
0 answers
48 views

after updating from: <package id="Google.Api.Gax" version="4.10.0" /> <package id="Google.Api.Gax.Grpc" version="4.10.0" /> <package id="...
mortenma71's user avatar
  • 1,316
0 votes
1 answer
128 views

I'm integrating Google Cloud Vision API into my Spring Boot app, but I keep getting the error: java.io.IOException: The Application Default Credentials are not available. They are available if running ...
Charfeddine Mohamed Ali's user avatar
0 votes
0 answers
246 views

I have explored the Google Imagen 3 Multimodal model to replace an object with another object generated by a prompt using the API. I am trying to explore the possibility of replacing an object with ...
DynaObject LLC's user avatar
1 vote
1 answer
58 views

I'm using Google Vision API TEXT_DETECTION (with Java) I got response successful. It's successful only fullTextAnnotation. and textAnnotation is empty.. I don't know why I used Vision API REST with ...
StarCue's user avatar
  • 71
0 votes
2 answers
307 views

I'm building a MAUI app in .NET8 which will scan barcodes. I'm trying to integrate the GoogleVision library - BarcodeScanner.Mobile.Maui (8.0.0.1) and I'm getting an error which I have no idea how to ...
Val's user avatar
  • 1,882
0 votes
1 answer
404 views

I was using google vision for OCR. but there is an offical announcement for Vision Deprecation so there is an vertex AI available. In that they mentioned a pre trained model for vetex OCR now to use ...
Shubham Nagar's user avatar
0 votes
0 answers
443 views

I am working on a face recognition based attendance system. I am using com.google.mlkit:face-detection library for face detection by camera image analysis. I am facing a problem with face spoofing i.e....
Kapoor Chand Saini's user avatar
1 vote
0 answers
64 views

I am working on a project where I have trained a custom machine learning model for object detection using Google Vision. However, I am unable to locate the option for exporting the trained model ...
shr33ya's user avatar
  • 11
0 votes
1 answer
144 views

I'm sure I'm missing something simple, but I can' get it to work: const request = { "requests": [ { "image": { ...
backwashphili's user avatar
1 vote
1 answer
223 views

I am trying to use google vision API from a Flutter app. I am using the google_vision package: https://pub.dev/packages/google_vision. From the example in this page: https://pub.dev/packages/...
Eran's user avatar
  • 11
0 votes
1 answer
108 views

I'm using google vision api for face detection, and once the face is detected I'm capturing the image. But if suppose a video is shown instead of real face, that is also getting detected. How to ...
Julie's user avatar
  • 1
0 votes
1 answer
153 views

So basically all I want is for Google vision to identify an Image of mine... I send the following request: to: https://vision.googleapis.com/v1/images:annotate?key= With Data: {"parent":&...
user3575649's user avatar
3 votes
1 answer
3k views

I'm using Google Spring Cloud GCP and getting errors since trying to upgrade spring boot 2.x.x to 3.x.x Description: Parameter 2 of constructor in x.MyService required a bean of type 'com.google....
D M's user avatar
  • 63
0 votes
2 answers
93 views

I got some strange JSON-like format from Google Cloud OCR. It doesn't have quoted keys, colons, or commas. text_annotations { description: "," bounding_poly { vertices { x: 485 ...
Pondzik's user avatar
  • 11
0 votes
0 answers
679 views

I basically wanna tell Google Vision to read from top to bottom, left to right. In this example you can see the part on top being recognized as last instead of first. I guess, i could painfully ...
Otm Shank's user avatar
2 votes
1 answer
1k views

I'm trying to find any information on the advanced_ocr_options[] under textdetectionparams of ImageContext. https://cloud.google.com/vision/docs/reference/rpc/google.cloud.vision.v1#...
Arun Tejaswi's user avatar
0 votes
0 answers
277 views

df = pd.DataFrame(columns=['locale', 'description']) for text in texts: df = pd.concat( dict( locale=text.locale, description=text.description ), ...
ksykko's user avatar
  • 11
1 vote
2 answers
2k views

Been testing MLKit and have noticed less accurate results when compared with Google Vision. One thing I do have enabled is languageHints for Google Vision e.g. image: { ...
Joshua Augustinus's user avatar
1 vote
1 answer
2k views

i ran the following code import io import os # Imports the Google Cloud client library from google.cloud import vision # Instantiates a client client = vision.ImageAnnotatorClient() # The name of ...
Sardar Raheem's user avatar
0 votes
2 answers
2k views

I'm working on implementing the Google Vision Detect Multiple Objects API in Python (https://cloud.google.com/vision/docs/object-localizer) The problem I'm having is that I don't know how to use the ...
James Parker's user avatar
  • 2,262
1 vote
1 answer
3k views

I am using google vision api. The key given to has been returning the same error over and over again [reason: "ACCESS_TOKEN_EXPIRED"]. I had my friend use the same key and run the same code ...
Nathan's user avatar
  • 11
1 vote
1 answer
540 views

I want to use the legacy text_detection and document_text_detection model. (refer: https://cloud.google.com/vision/docs/service-announcements) Im trying it this way using features: import io from ...
Sumant Agnihotri's user avatar
0 votes
1 answer
201 views

So I have some code that gives three syntax errors but IT RUNS FINE, it almost like the syntax error are cosmetic or something. Its in a very large project that used googles cloud vision API, I might ...
CrimsonOcean75's user avatar
1 vote
1 answer
3k views

I am using Google ML Kit to do selfie segmentation (https://developers.google.com/ml-kit/vision/selfie-segmentation). However, the output am getting is exteremely poor - Initial image: Segmented ...
sppc42's user avatar
  • 3,326
5 votes
2 answers
7k views

I'll premise that I've already googled and read the documentation before writing, I've noticed that it's a popular discussion here on StackOverflow as well, but none of the answers already given have ...
Eugenio's user avatar
  • 128

1
2 3 4 5
15