Microsoft

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.

  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. Image size limitation, have to adjust image to 50x50 pixels

    Image size limitation should be improved. I have to get images larger than 50x50 pixels to work. This value should set smaller.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  2. OCR processing of numerical text should not be impaired when detected language is Turkish

    When testing with Turkish text that also includes numerical strings, I have isolated the following anomaly:

    Consider two versions of an otherwise identical image (for informative purposes, the image is a graphic depicting the total number of deaths in Turkey from COVID-19, on a particular date):

    Turkish version:
    TÜRKİYE’DE ÖLÜMLER 1.368

    English version:
    DEATHS IN TURKEY 1.368

    When the image is OCR-processed with the text in English (i.e. with the words: “DEATHS IN TURKEY”), the numeric string is returned correctly as “1.368”.

    However, when the image is OCR-processed with the text in Turkish (i.e. with the words: “TÜRKİYE’DE ÖLÜMLER”), the…

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  3. OCR return wrong text with very low confidence score

    OCR misread letter "l" to "i" and return 0.355 as confidence score. Is this a bug?

    The email part OCR service return as "Email: vi@bimco.org" with confidence score 0.355 while the rest is correct parsing with confidence score always higher than 0.9. I used the same file with different OCR providers and only your service return wrong value.

    I tested the service with different pdf file and sometimes, it parse wrong "f" and "r" as well.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  4. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  5. Ensure that all pages are returned, even ones that Computer Vision is unable to extract text from.

    If a document consists of pages that contain font of a 'good' size and then some documents (think Terms and Conditions) that contains a lot of small text that can't be interpreted by Computer Vision then it gets excluded from the response.

    The page numbers are returned - so this is useful. But in the case where a 'complicated' page is the last page, this would not be returned, so the number of pages you believe you have would be one less than the number of pages you actually have. Including (at the very least) a JSON segment with:
    {…

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  6. Ensure the OCR File Size

    The German guide says image size for the OCR has to be between 50 x 50 and 4200 x 4200 pixels, with no additional info to file sizes (JPG in my case). However, files larger 3000 x 3000 are rejected in my case. Am I missing something?
    Thanks in advance

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  7. Is it recommendable to perform any pre-processing on images or PDF before using the Read API? OCR

    I suppose noise-reduction and binarization is already done on your side right? Or do I have to pre-process documents and images before feeding them into the API?

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  8. Not Detecting Space Between Middle Initial and Last Name

    We have printed documents with a person's name that includes their middle initial (without a period i.e. JOHN A DOE). Azure OCR usually detects a space between the first name and middle initial but not the middle initial and last name.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  9. Signature Recognition

    How does one recognize handwritten signature within a PDF or word document ?

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    2 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  10. Please, make a support for bulgarian language

    It's not so hard to add Bulgarian language once you have Russian (cyrillic).

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  11. 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
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  12. 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
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  13. spanish

    Spanish support for batch processing will be appreciated

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  14. 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
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  15. 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
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  16. I want to extract only text.

    ocr api I want to get only the text recognized as a result. What should I do?

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  17. 7 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  18. RecognizeText(Printed) is not recognizing the pound symbol (£)

    I have many cases of pictures of texts where one can find a pound sign (£) but the sign is NEVER correctly recognized by Azure Cognitive Services RecognizeText API, as far as I tested. Other symbols, like the dollar sign ($) for example, are identified without problems.

    I made tests with print screens of texts containing £, since these should be easy for the OCR tool to convert, and again the pound sign is not correctly identified (it becomes an f, a 2, a 1, a $ etc).

    I am suspecting that the pound sign is not included in the…

    18 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    2 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  19. Response should contain column and row indices

    Why should I have to calculate row and column indices? You're processing this data and know those numbers exactly. This data is far more valuable (at least to me) than your IList<int> of 1 -> n integers (bounding boxes) - that itself could use some reorganization. I'm testing out the big 3 OCR engines - Amazon, Google and Azure - Azure so far has the best scan results, but the poorest return object IMO.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  20. 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
    0.5065

    When 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
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Text Recognition  ·  Flag idea as inappropriate…  ·  Admin →
← Previous 1 3
  • Don't see your idea?

Feedback and Knowledge Base