Form Recognizer
-
selectionMark recognition not working properly
I'm using forms with lots of check box fields (ACORD 28). With the 2.1 beta I'm finding that the labeling tool does not always recognize a check box (e.g. selectionMark) as a check box. Many times it will simply think it's a text field and will not allow me to identify it as a selectionMark type. The reverse is also true. Sometimes if I try to label a field as String it will tell me the type is not compatible because it assumes it's a selectionMark. I think you need to take a different design approach for selectionMark labeling and…
2 votes -
What is the best way to train 1k different vendor invoices for custom model train? as there is a limit of 500 pages per model id
What is the best way to train a model having 1k vendor invoices, as there is a limit of 500 pages.
As per the limit mentioned we can max 100 vendor invoices per model id.Can you please put some light on this from the implementation perspective ?
4 votes -
Dates in format dd MMM yyyy not being processed correctly
When a document has a date in the form "31 Dec 2020" (dd MMM yyyy) the forms recognizer doesn't process it correctly.
This is despite setting up the associated tag as type "DATE" and format "DMY"
The resulting value valueDate is not listed.
1 vote -
labeling tool improvements
Add regex option to form tag format. Let users specify what is expected result and help FR filter out text that does not belong to expected value. validate result with regex and adjust confidence score accordingly.
modify recognized field in training form. Sometimes recognized value is incorrect and contains additional text. I would like to be able to flag and correct this value so FR would better recognize this type of mistake
Add versioning to trained models. Models are immutable, but they belong to a same project. Show a list of previously trained models, so users could switch between them…
3 votes -
Form Recognizer Container for passport image
My goal is to extract data from client passport image in a key value format for which I tried Form Recognizer Container (Cognitive Service Form Recognizer API V1 Preview v1). But the results where not satisfactory since the model created from training data was not able to extract any key value pair. I tried various training sample and also referred https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/build-training-data-set but didn’t work
Can you please guide me how can I extract the data in a required format ?Any help is much appreciated, Thanks
1 vote -
CSV as output
Please add feature to obtain table data as CSV which makes it easier to use ETL tools like ADF for loading data into relational database
1 vote -
Publish sample C# client code that compiles and works
When I copied and pasted the sample C# client code snippets from the Quickstart documentation, the code doesn't even compile. Please share a simple working C# client program via github so we don't have to copy/paste bits and pieces and we don't have to struggle with compiler errors. The sample should work as long as the FORMRECOGNIZERENDPOINT and FORMRECOGNIZERKEY environment variables are set to valid values. [Oh, please make this textarea box resizable]
2 votes -
Problem [open cloud project]
When I used label tool to open the project from cloud, it will auto create the same connection in my Connections setting.
This situation can be fix?1 vote -
OCR validate text detection
Often, OCR detects handwritten text incorrectly.
For example:
"Bridget Sims, MD" was detected at "Bridge+ Sims, MD"
There should be a way to correct this and enter in the correct value of the text detected as "Bridget Sims MD" after the OCR has done its work.
Is there a way to do this already?
4 votes -
Can't create a project
Hello, I followed the tutorial here: https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/quickstarts/label-tool
I setup a Azure web app (ACI) to run the docker image according to this tutorial: https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/deploy-label-tool#deploy-with-azure-container-instances-aci
I setup the connection. Then when I went to create the project it kept giving me this error and I have no idea what is wrong? I tried removing all spaces and non alpha characters from project name but nothing seems to work :(
2 votes -
Group Custom Models by Forms Types
I am using a single storage container having different types of forms.
Is it possible to generate different custom models with labeling based on the form types. For Example, one Model Id for W2 wage form and other Model Id for 1040 tax form etc..
Is there any possibility to filter the tags based on Form Types. It is very confusing to see all the tags of different form types spanning across all different forms.
Is it possible to store the training data on premise.
1 vote -
Allow to add a name to model when training
Hello,
it would be nice to allow to name the model when training.. will allow to not waist time saving id ect
4 votesThis is now supported in the v2.1 preview
https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/whats-new#august-2020
-
Process multiple documents contained in a single file
I’m working on a project to create custom Machine Learning models for the processing of invoices using Azure Form Recognizer and OCR Form Labeling Tool.
In general it’s working really well, however, I have a situation where I have more than one invoice in the same PDF file. In is current form, the OCR Form Labeling Tool & Azure Form Recognizer don’t handle this situation very well. I‘m wondering if there are any tips or guidelines for this situation or will this use case be covered in the future?
Any guidance would be greatly appreciated!!
7 votes -
Use My Own OCR to capture other languages? Or when will support Simplified Chinese.
Can i use my own ocr service to capture text ? Cause many languages are not supported and there is no schedule.
2 votesSimplified Chinese is now available in v2.1 public preview.
https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/whats-new#august-2020
-
Limit processing to first X pages
We should be able to use a setting to only analyze the first X pages of forms.
I.e. we have forms related to phone bills, which the first 2 pages have relevant info then there is 20+ pages of just call records which we do not want to analyze.
We should be able to tell the analyze forms function to only process the first X number of pages.Especially in the power automate function.
6 votes -
Max number of custom models
There is a max number of custom models that I can create?
For example, If I trained a custom model from a dataset and I add more files to this dataset, I need to delete the old one and use the new one?
1 vote -
Simplify Local file path of Training source for cross platform mobile use (Xamarin)
The API console struggles with the local file path definition and I don't always want to use embedded assets/resources in Xamarin projects. So is there a robust/consistent way to use local file path (say for Android/iOS) - and is the only option the local application data folder?
1 vote -
Train using URL sources other than Azure blobs??
This query may already be out there...apologies in advance...
Is there any roadmap/plan to add general URL sources for Training api other than azure blob containers?
(Have a separate question relating to local file paths)2 votes -
What's the best way to train a table without line? (See Pic)
I know Form Recognizer does not yet support labeling tables as tables. Suggestions please.
Please see pic1 for reference. Number of Line Items may vary at large.
And, What can we do if some text is not recognized by the OCR labeling tool see pic1 ?8 votes -
2 votes
- Don't see your idea?