Computer Vision
Welcome to the Computer Vision API Forum
Categories
API – Any ideas or feedback pertaining to features or enhancements to Computer Vision API.
Documentation – Any ideas or suggestions for the API Reference or Documentation.
Language Support – Submit a request to have a particular language supported.
Samples & SDK Request – Let us know if you would like to see a Code sample or SDK provided.
Custom/Sample Images – Have an image you’ve tested and not getting the results you are seeking? Upload the image and describe the information or tags you would like to be included.
Attention!
We have moved our Customer Feedback & Ideas for Azure Cognitive Services portal to the Azure Feedback Forum.
-
Hindi (Devanagri) Language Support
This API has limited language support. Please do include more languages support as well. Or please share the idea of creating our own custom language train models and use them as our source language.
1 vote -
1 vote
-
Can handwriting(Japanese) be supported?
Can handwriting(Japanese) be supported?
2 votes -
Please, make a support for bulgarian language
It's not so hard to add Bulgarian language once you have Russian (cyrillic).
1 vote -
Better support for artistic fonts.
Artistic fonts like the ones found in comics are really hard to recognize, especially for North East Asian languages.
Fix that, Google equivalent ocr option handles it a ton better.
1 vote -
Fractions not recognized --
Fractions are not being recognized..
many different combinations and characters attempted. Probably similar to symbols issue. Alternative-- How can I train a model to deal with this? I am previewing Form Recognizer but suspect similar results.1 vote -
Unable to handle ₹ ( Indian rupee symbol ) converted to 3 while detection
Currently vision API is not able to handle ₹ (INR) symbol.
It converts it to 3. So if you want to detect amount ₹ 49, you will get 349 as output.1 vote -
Add German Umlaute and ß to the Computer Vision API
Hello,
i'm using the handwriting recognition of the Computer Vision API to describe certain german documents. therefore i'm in need of the umlaute aswell as the ß sign. are there any plans on supporting this? sadly the localizable ocr results are not accurate enough.
Regards
1 vote -
The PDF coordinate system needs some work
The Read api (https://westus.dev.cognitive.microsoft.com/docs/services/5adf991815e1060e6355ad44/operations/2afb498089f74080d7ef85eb) does not handle PDF word coordinates correctly.
Did not see a way to report the bug on the API page, so I am reporting it here.
I am sending it a 8.5x11 page and getting coordinates in inches that are outside the box.
The width is marked as 10.9833 and height as 8.4567, however it is getting words outside that box:
12.3419
0.4349
13.2572
0.4294
13.2715
0.501
12.3562
0.5065When I print the coordinates to the page some documents are spot on the the x coordinate, but roughly half as far down the page…
5 votes -
Improve accuracy for combination of numbers and special characters
When i try to detect license number from image of pattern 12/234232/3454, the slash symbol is recognized as 1.
2 votes -
Information on Computer Vision Image and Data Retention
People need to know what you are doing with their images during and after processing. Please have a clearly stated policy on this.
3 votes -
i need to find some kind of objects like cars or phones
i want to filter the search about a object or something in the image
1 vote -
Recognize Vancouver Olympic Torch in photo
Photo of landmark in Vancouver, Canada is incorrectly identified as "a plane parked on the side of the road" - it should at least be identified as a monument or sculpture.
1 vote -
Please provide the taxonomy for tagging and taxonomy used for object detection in the documentation.
Please provide the taxonomy for tagging and taxonomy used for object detection in the documentation.
It would fine if it is not an exhaustive list. This taxonomy would be more helpful to users to set predefined conditions for objects or tags.
2 votes -
Generate Human friendly operationId in swagger
Almost all tools that can generate API Client out of Swagger API defenition, will use OperationId to generate method name in a client. In your swagger API, OperationIds looks like "56f91f2e778daf14a499e1fa", and in C# it will produce method name public System.Threading.Tasks.Task 56f91f2e778daf14a499e1faAsync();
It's extremely hard to recognize what method doing, based on this operationIDPlease, modify operationIds in a swagger documentation https://westus.dev.cognitive.microsoft.com/docs/services/5adf991815e1060e6355ad44/export?DocumentFormat=Swagger&ApiName=Computer%20Vision%20API%20-%20v2.0 to make it human and code generator tools friendly.
P.S. I got this swagger file from https://westus.dev.cognitive.microsoft.com/docs/services/5adf991815e1060e6355ad44/operations/587f2c6a154055056008f200
2 votes -
1 vote
-
Recognize halogram in picture
When analyzing regular pics vs. Pics with Halograms embedded inside
1 vote -
API do find duplicates in Images
Function to search in whole Blob with Images to recognize duplicated images.
5 votes -
How far has the API gone with trying to detect people from the back view?
Can the API detect humans even from a back view. It might not be very accurate just like humans but after you have lived with someone else for a long time there is a high chance that you can guess who they are even from a back view. Therefore was wondering if the computer detected multiple images of people even from back view whether it would be able to guess.
1 vote -
Add A Quickstart Guide.
The guide for recognizeText is not available for php. So I would like to add one. How should I add?
2 votes
- Don't see your idea?