How to customise AWS Textract? - amazon-web-services

So far my Textract tests are very impressive for handwriting, but I see sometimes it fails to recognise some forms and some values. Is it possible to train it? If I'm scanning the same type of form/document it will be very useful to amend the results and teaching it where the boundaries of some form elements lie and some key-value associations as well?
It will be a real deal breaker for the kind of service I'm trying to design.
Thanks in advance.

No. It is not possible to 'train' Amazon Textract.
The available actions are limited to analysing a document and detecting text.
See: Actions - Amazon Textract

I know this is an old post but I am working on a project to do exactly this. You can look at this Hugging Face model and the referenced model in Github:
https://huggingface.co/docs/transformers/model_doc/layoutlmv2
It isn't simple but it's the only open source solution I know of.

Related

Microsoft Cloud For Sustainability on MS Dynamics - is there any demo data available/accessible, extended multilingual support?

I am trying to wrap my head around Microsoft Cloud for Sustainability. Apparently it's a solution based on Microsoft Dynamics. I need to have more back-end to that solution, because as it is right now I'm either lacking permissions (or extra paid access to Microsoft resources) or missing a chunk of documentation, because I'm unable to:
Change default language across the board - I can switch MS Dynamics to any language I want, but it will work for a shell only. Anything that's CfS specific, is in English. Do I remove the demo data and import my own scopes and data? As only thing available are database and Cube for BI analytics and JSON files describing CfS structure in general (that's in CDM), do I really have to create it from scratch? This brings me to second question:
Access entry-level data that's already in demo version - I need to see what's in the database the CfS is using, or be able to modify it. Is there any way to get to it via Business Central, if at all possible?
Since I will be preparing several presentations for potential customers, I need a way to quickly create a dataset based on initial and very basic information provided by each customer, how can I do that with trial user
I work for a company that's Microsoft Certified Partner, so logically resources for what I need should be available to me, but either links in the documentation are dead (and some are, as they redirect to general info) or require some special access level (or are dead, but error message is really not helpful at all).
Is there somewhere else I can go? The Documentation page offers little towards what I need...
P.S. I think I should tag this question with CfS specific tags, but not enough rep...

Create a model with google ML natural language or other potential service

So I have been collecting data of numerous text-descriptions about articles, where as each description was structred differently. Now, I would have to "create" an algorithm, which sorts out the title of that article for me what is a hard task. I have come around Google ML natural language and it seems to be able to create one for me.
Unfortunately, I am not really able to exactly find out how I can use it,
so my question is... How precisely can I set it up ? And additionally, it would be helpful to know if firebase has such a service, since I am planning to build a firebase project.
Thanks in advance for any help !
Unfortunately models created using Google AutoML Natural Language are not exportable to Tensorflow lite (mobile models). Based from your use case you will need a model for text classification, the provided link has a sample of how this model work. You can follow this tutorial to train a custom model using the data that you have so it can identify if a title of a article is a hard task or not.
Once training is done you can now:
Deploy it in Firebase
Download the model in your device and perform testing.
You can find detailed instructions from training the model to testing it on your device for either iOS or android.

Does AWS Comprehend classify images?

I am fairly new to AWS Comprehend. I know that AWS Comprehend can custom classify documents (Text Files). Does, AWS Comprehend also classify Image files? Also, while training the model, is it necessary to give the entire document text in the CSV or will just keywords do?
The reason being, I want to built a custom classifier that can classify invoice, Pay Stubs and few other such document types which are in image formats. Can Comprehend do this? If so how?
Googled quite a lot but couldn't find anything much relevant around. Really appreciate your help with this.
Thank you!
Comprehend doesn't do this natively, so you would have to build a solution. Something you could try is to combine Amazon Textract (for extracting the details from the documents) and then Comprehend to classify them.
From the FAQ, Textract calls out this as a common use case. I couldn't find an exact example of someone doing this, but it is directly called out in the documentation.
Amazon Comprehend only works on text.
Amazon Rekognition works on images.
AWS has all the building blocks to accomplish this, but you will have to configure/build this yourself. You can use AWS Textract to extract all the text from a document, and then pass the text into the AWS Comprehend service to do the classification for document type.
Before you can do this you need to train the machine learning part of Comprehend to do the correct identification of the document types. You need to configure and train a custom classifier in AWS Comprehend where you supply a CSV file with a list of classifications for example 'document type' and then text that would be in the type of document. If it is just forms then you can use Textract Form feature to only get key value pairs, then use the keys (labels in the form) as text for the custom classifier.

Amazon Alexa: Is the code available for built in skills?

while writing custom skills for Alexa using Lambda functions, I was just wondering if there is code available for built in skill sets.
Does anyone have an idea about it?
As far as I know the code is not available.
Also some of the built in skills seem to be able to do things that not all third party apps can do so you may come up short if you are trying to replicate functionality.
If you are just looking for sample code the best place to check out is the Alexa Github samples. They show you how to do a variety of thing from setting up your Lambda function to interacting with a few different models.

Amazon inspector

I would like to use AWS tool, like in topic. To me it looks like there are two releases of this tool. One with AWS agent installed on EC2 instance, allows tracking security issues. New one with some benchmarking, and so on. So I'm interested in the new one.
I've red docs, set up sample, test env. but still it looks a bit unclear for me. I understand that they are using public database of vulnerabilities. As well as benchmarking, or testing against best practices.
The question is - how can I know that all of that is tested in lowest 15min. target? Or in the other words - if time is short - what is less tested?
Is anyone use this tool and would like to share knowledge, insights?
A report provided at the end of the testing gives you an overview of the scanning results. The results indicates which of your preselected resources has security issues.