How to use Google Cloud Video Intelligence Celebrity Recognition? - google-cloud-platform

I have been using Google Cloud Video Intelligence Api happily and succesfully until this point. However, now if I am not mistaken, I noticed that Celebrity API is only open to approved selected media companies. Amazon Rekognition provides this support to public. This is quite unbelievable. How can this kind of service be a private service on such a public cloud service such as Google's ?
Does anyone know how to use Celebrity Recognition API from Google Cloud ?

In answer to your question why Celebrity recognition is not made publicly available, there are legal reasons that Google may be dealing with. This type of technology is powerful and in the wrong hands could cause serious issues for all parties involved.
See the “Restricted access feature” note in Google’s documentation [1].
[1] https://cloud.google.com/vision/docs/celebrity-recognition

Related

Fine tuning on either Google Cloud Vision, Microsoft Azure Computer Vision API or Amazon Text Extract

I need to transcribe a large number of Handwritten documents. I tried to use cloud services from either Google, Amazon, and Microsoft. Namely:
https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/
https://cloud.google.com/vision/docs/handwriting
https://aws.amazon.com/textract/
Unfortunately, none of them achieved good enough results. I suspect it is because my documents have a weird handwriting style, and as a result, the networks struggle a lot.
I searched whether I could fine-tune (with manually transcribed data), but I have not found anything online, so as a last resort, I ask here.
If it is possible to fine-tune one of these models, could you please point me some resources?
You are correct, with Azure Cognitive Services with Computer Vision you cannot upload your own data to train the API to recognise the handwriting in your documents I'm afraid. I can't comment on the other offerings from AWS and Google I'm afraid, but certainly not for Azure.

Google Cloud Vision - Which region does Google upload the images to?

I am building an OCR based solution to extract information from certain financial documents.
As per the regulation in my country (India), this data cannot leave India.
Is it possible to find the region where Google Cloud Vision servers are located?
Alternately, is it possible to restrict the serving region from the GCP console?
This is what I have tried:
I went through GCP Data Usage FAQ: https://cloud.google.com/vision/docs/data-usage
GCP Terms of Service:
https://cloud.google.com/terms/
(Look at point 1.4 Data Location on this page)
Talking to the GCP Sales rep. He did not know the answer.
I know that I can talk to Google support but that requires $100 to activate, which is a lot for for me.
Any help would be appreciated. I went through the documentation for Rekognition as well but it seems to send some data outside for training so not considering it at the moment.
PS - Edited to make things I have tried clearer.
For anyone looking at this topic recently, Google Vision has introduced multi-region support in December 2019, as can be see in their release notes.
Currently Google Vision supports 2 different processing regions: eu and us, and they say that using a specific endpoint guarantees that processing will only take place in the chosen territory.
The documentation for regionalization mentions that you can simply replace the default API endpoint vision.googleapis.com with either of the regional ones:
eu-vision.googleapis.com
us-vision.googleapis.com
The vision client libraries offer options for selecting the endpoint as well, and the documentation gives code samples.
For example, here is how you would do it in Python:
from google.cloud import vision
client_options = {'api_endpoint': 'eu-vision.googleapis.com'}
client = vision.ImageAnnotatorClient(client_options=client_options)
As pointed out by #Tedinoz in a comment above, the answer can be found here: https://groups.google.com/forum/#!topic/cloud-vision-discuss/at43gnChLNY
To summarise:
1. Google stores images uploaded to Cloud Vision only in memory
2. Data is not restricted to a particular region (as of Dec 6, 2018)
3. They might add data residency features in Q1, 2019.

Google Cloud APIs usage data by projects

Is there any way to programmatically get data similar to APIs overview of Google CLoud dashboard. Specifically, I'm interested in the list of APIs enabled for the project and their usage/error stats for some predefined timeframe. I belive there's an API for that but I struggle to find it.
There's currently no API that gives you a report similar to the one you can see through the Google Cloud Console.
The Compute API can retrieve some quotas with the get method but it's somewhat limited (only Compute Engine quotas) and, for what I understood from your question, not quite what you're looking for.
However, I've found in Google's Issue Tracker a feature request that's close to what you're asking for.
If you would need something more specific or want to do the feature request yourself, check the "Report feature requests" documentation and create your own. The GCP team will take a look at it to evaluate and consider implementation.

Google Cloud Speech-to-Text API - Multi-speaker recognition?

The new Google Cloud Speech-to-Text API is said to be the best in the market. Does it provide speaker annotation (or other speaker information) at all? Like who says what at what time. I can't seem to find anywhere on its documentation or examples provided that mentions it.
Both IBM and Amazon do it.
I'd be appreciated if anyone can let me know, thanks!
Individual speaker recognition is not currently a feature provided by the API. It’s noted in the issue tracker [1] as a feature request, however there’s no ETA for it currently. I’d recommend starring the issue to receive future comments and updates regarding it.
[1] https://issuetracker.google.com/35901846

Google Speech API compliance in Canada

A customer I am working with wants to use Google Speech API for transcribing audio but there are compliance concerns.
I know that you can upload files directly or have the API access files in Google Cloud Storage. For either of these methods is anyone familiar with how they interact with the data compliance laws in Canada?
For instance if the audio files are uploaded to a Cloud Storage bucket at the Montreal datacenter and we make an API call on it does the file ever leave that datacenter?
Thanks in advance for any insights!
Stack Overflow is not a great place to get a legal opinion, but is there a particular standard for compliance that they require? Google Cloud has a number of international data compliance certifications, one of which might be the one your customer requires. Talk to your customer and see what they need, and take a look at Google Cloud's list of standards that they are compliant with to see if it meets those needs: https://cloud.google.com/security/compliance
For example, the Cloud Speech API is compliant with ISO 27018, an international standard for cloud service privacy. Is that sufficient for your customer? You'll need to ask them.