AdminSanjeev Jagtap
(Admin, Microsoft Cognitive Services)
My feedback
-
2 votes
An error occurred while saving the comment -
1 vote
An error occurred while saving the comment Vince - Do you mean when the document contains tables and you would like to know the cells and their row and column indices? if yes, you should check out the other product from our team - Form Recognizer's Layout API feature that outputs table and checkbox details in a document.
https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/overview#layout-api
-
2 votes
An error occurred while saving the comment Please share a test image and make sure you are using the latest Read 3.0 API described at https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-recognizing-text.
-
1 vote
An error occurred while saving the comment Hi, please use the new Read API 3.0 that supports German language among others. The input requirements are listed at:
https://docs.microsoft.com/de-de/azure/cognitive-services/computer-vision/concept-recognizing-text#input-requirementsSupported file formats: JPEG, PNG, BMP, PDF, and TIFF
For PDF AND TIFF, up to 2000 pages are processed. For free tier subscribers, only the first two pages are processed.
The file size must be less than 50 MB and dimensions at least 50 x 50 pixels and at most 10000 x 10000 pixels.
The PDF dimensions must be at most 17 x 17 inches, corresponding to legal or A3 paper sizes and smaller. -
2 votes
An error occurred while saving the comment Hi, Can you please share the test images you mention? That seems like a bug, not by design. Thanks!
-
2 votes
An error occurred while saving the comment Ashish,
Can you please upload your test image here for testing? We are constantly working to improve the quality of the service. Thanks for the outreach. -
1 vote
An error occurred while saving the comment There is no need to do any image pre-processing on the images or PDFs before submitting them.
-
14 votes
An error occurred while saving the comment Hi, We are constantly working to improve the AI quality and single character recognition is one of the focus areas. Read 3.0 improves on previous releases and upcoming releases should further show improvements. Be sure to upgrade to the latest API version if you are using Read 2.0 and older.
John, improving extraction of single characters especially 1s and Is and 0s and Os is a focus of our ongoing improvement work. Thanks for the reminder!