Azure Computer Vision
An Azure artificial intelligence service that analyzes content in images and video.
338 questions
1 answer
One of the answers was accepted by the question author.
Image descriptions, captions using azure vision
i saw a blog post https://blogs.microsoft.com/ai/azure-image-captioning/ they talking about the new image descriptions and when i tested they give me the same old descriptions how to use the new version to get the more accurate image…
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(73.60000000000001, 20%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EP%3C/text%3E%3C/svg%3E)
1 answer
Best practices for arabic OCR
I am trying to extract all the information given in an Egyptian national ID which mainly contains Arabic letters and digits. I am doing this using Azure's OCR API. The API is working but so far it is inaccurate. What are the best practices that I can use…
asked 2021-06-20T07:44:16.277+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(80, 54%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAG%3C/text%3E%3C/svg%3E)
Amro Ghoneim
116
Reputation points
commented 2021-06-21T09:24:15.29+00:00
Amro Ghoneim
116
Reputation points
1 answer
One of the answers was accepted by the question author.
Using Azure OCR, some of the text is considered part of a table instead of on the same line but separated by large spaces. Can the tables be disabled ?
I'm using the endpoint https://test-ocr-mike.cognitiveservices.azure.com/ and supplying an image that is all text with the exception of a logo. In the body of the image the data seems to be apparently visually separated by columns, no column lines are…
asked 2021-05-31T17:56:03.727+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(230.39999999999998, 50%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMM%3C/text%3E%3C/svg%3E)
Michal Muller
21
Reputation points
commented 2021-06-01T20:14:55.6+00:00
Michal Muller
21
Reputation points
1 answer
Duplicated words returned from computer vision API
Hi, I'm using read API to extract typed and handwritten text from pdf. When pdf is scanned, all is working as expected. However if pdf is already OCRed, then json response of extracted text has duplicated words and phrases (with some duplicates…
asked 2021-05-11T11:20:33.47+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(294.40000000000003, 94%, 38%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJS%3C/text%3E%3C/svg%3E)
Julia Sizova
1
Reputation point
commented 2021-05-28T05:17:28.71+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(22.400000000000002, 11%, 12%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ERM%3C/text%3E%3C/svg%3E)
Ramr-msft
17,651
Reputation points
1 answer
One of the answers was accepted by the question author.
Computer Vision API 2.0
We are using this endpoint now: /vision/v2.0/areaOfInterest How long will it be possible to use this endpoint? The latest version seems to be 3.2 now. Time to upgrade?
asked 2021-05-24T07:26:50.637+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(128, 8%, 22%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EA%3C/text%3E%3C/svg%3E)
Anonymous
accepted 2021-05-25T08:28:05.537+00:00
Anonymous
1 answer
Computer Vision API output in docx format
Can I get the output from Computer Vision API in docx format for further editing with MS Word?
asked 2021-05-21T11:42:21.977+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(19.2, 67%, 11%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EDR%3C/text%3E%3C/svg%3E)
Dariusz Rosłon
1
Reputation point
commented 2021-05-24T08:37:48.007+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(278.4, 1%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EYM%3C/text%3E%3C/svg%3E)
YutongTie-MSFT
48,001
Reputation points
1 answer
One of the answers was accepted by the question author.
InvalidImageSize error for 9600x7200 size image
Hi, we are a small team trying to extract data from engineering drawings using Python (These diagrams are fairly dense with lines with sparse information). We have encountered an error where the HTTP error code we get for our request is 400 when sending…
asked 2021-04-29T21:46:25.227+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(150.4, 82%, 24%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EP%3C/text%3E%3C/svg%3E)
Pranav_Annapareddy
21
Reputation points
accepted 2021-05-11T16:04:28.767+00:00
Pranav_Annapareddy
21
Reputation points
1 answer
People Counter Web App displays no data
When I deployed the people counting web app demo, the app didn't seem to be pulling any data. It would say 0 piplines. ![93577-image.png][1] [1]: /api/attachments/93577-image.png?platform=QnA I contacted chat support earlier and a rep,…
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(76.8, 98%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ETD%3C/text%3E%3C/svg%3E)
1 answer
Microsoft.rest.clientRuntime nuget package dependancy error
Hello I'm trying to use the Microsoft Azure API for OCR. I am trying to use it in a RelativityOne program(c# application) which needs .NETFramework 4.6.2 or later. Microsoft.Rest.clientRuntime needs .NETFramework 4.6.0 or 4.6.1. When i try run this i…
asked 2021-05-04T01:05:55.317+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(192, 98%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EOT%3C/text%3E%3C/svg%3E)
oscar toohey
1
Reputation point
commented 2021-05-04T22:58:44.28+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(214.4, 45%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EGM%3C/text%3E%3C/svg%3E)
GiftA-MSFT
11,161
Reputation points
1 answer
Content Tags - Computer Vision - Documentation
Hi there, I work with software that uses Microsoft's content tagging and was wondering if there was any documentation available that touches on standards Microsoft uses for their tags. For example some users search "Building Outdoor" vs…
asked 2021-04-29T20:22:31.97+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(124.80000000000001, 65%, 22%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ECW%3C/text%3E%3C/svg%3E)
Chris Winsor
1
Reputation point
answered 2021-04-30T18:20:05.777+00:00
GiftA-MSFT
11,161
Reputation points
1 answer
Read API unexpected responses
For the past few months, when invoking Azure Read API, we have been receiving invalid responses from the server, like "downstream duration timeout", instead of a valid JSON as specified in the documentation. This causes parsing errors and is…
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(0, 19%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EY%3C/text%3E%3C/svg%3E)
1 answer
Is the Face API based on the work of Paul Ekman?
Does the Face API use Paul Ekman's FACS as its basis? Does it calculate the measurement of Action Units? Or is it based on something else entirely? How does it come to its individual emotion identifications and measurements?
asked 2021-04-26T19:13:51.39+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(6.4, 71%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EOO%3C/text%3E%3C/svg%3E)
Osc O
1
Reputation point
answered 2021-04-26T23:37:13.073+00:00
GiftA-MSFT
11,161
Reputation points
0 answers
Read operation on operation id got from azure read api
I am trying to read the data in operation id url but for that I have to use settimeout function and set some time , if I use it without settimeout it alway's shows status is runing . const read_result = (opid) => { var dlres; var config = { …
asked 2021-04-20T15:11:30.877+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(118.4, 84%, 21%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ECB%3C/text%3E%3C/svg%3E)
Chetan Bawankule
1
Reputation point
commented 2021-04-21T06:06:18.357+00:00
Chetan Bawankule
1
Reputation point
0 answers
Computer Vision Read operation uses two API calls
Hi, Yesterday I noticed that whenever I upload a file to Azure Computer Vision for "Read" operation it consumes two API calls instead of one. The code I'm using is 80% based on official Microsoft code samples. For last few months all API calls…
asked 2021-04-02T07:24:26.81+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(112.00000000000001, 8%, 20%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ERS%3C/text%3E%3C/svg%3E)
Radek Szuban
1
Reputation point
commented 2021-04-06T17:01:45.707+00:00
YutongTie-MSFT
48,001
Reputation points
1 answer
Uploaded Image for Computer Vision API?
I have question about the Azure Cognitive Service – Computer Vision API. I upload our image at Computer Vision API "Read"…
asked 2021-03-30T16:51:25.02+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(176, 76%, 27%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESK%3C/text%3E%3C/svg%3E)
Sethumadhavan, Kandavel
1
Reputation point
answered 2021-03-30T22:48:09.733+00:00
GiftA-MSFT
11,161
Reputation points
1 answer
OCR seems to get characters wrong.
I am throwing a few documents at computer vision in order to extract the text within them. These documents contain no hand-written characters, and the font used in the document seems to be reasonably easy to read. (however I am not a computer), …
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(89.60000000000001, 42%, 18%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EN%3C/text%3E%3C/svg%3E)
1 answer
Text content missing from the returned PageResult in Java sdk
Hi, when testing computer vision java sdk with two similar pdf files (one Englist, one French). Some string visible in the pdf files are not reported by PageResult when testing with one version of pdf, although they read properly from another version of…
asked 2021-03-17T13:43:31.773+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(179.20000000000002, 5%, 27%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EHL%3C/text%3E%3C/svg%3E)
Haiquan Li
1
Reputation point
commented 2021-03-22T08:04:47.75+00:00
YutongTie-MSFT
48,001
Reputation points
1 answer
READ Task canceled: system.Threading.Tasks.TaskCanceledException: A task was canceled
I am getting some READ OCR errors that is printing the message shown in the screenshot below. I am using the code provided by Microsoft in their getting started guide. I am running the code with multiprocessing (4 cores) so there are multiple calls to…
asked 2021-03-08T16:14:15.523+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(297.6, 18%, 38%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EBS%3C/text%3E%3C/svg%3E)
Baruch Shadrouz
31
Reputation points
commented 2021-03-12T20:18:07.077+00:00
GiftA-MSFT
11,161
Reputation points
1 answer
READ Missing Easy to Read Text
I am using the Get started code that is provided by Microsoft on how to use the READ API. I am running the READ with multiprocessing so I have 4 cores using calling the API at the same time. I am doing this because I need to test the accuracy for many…
asked 2021-03-08T15:49:44.75+00:00
Baruch Shadrouz
31
Reputation points
answered 2021-03-08T18:30:36.99+00:00
GiftA-MSFT
11,161
Reputation points
1 answer
Getting Different result when I run Computer Vision API on Python versus Example
In the computer vision client there are 2 different ways to tag an image. --> computervision_client.tag_image_in_stream and ** computervision_client.describe_image_in_stream** Code is as following from azure.cognitiveservices.vision.computervision…
asked 2021-02-27T18:56:34.257+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(310.4, 26%, 40%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EO3%3C/text%3E%3C/svg%3E)
ODL_User 310106
1
Reputation point
commented 2021-03-03T13:07:11.337+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee