Azure Computer Vision
An Azure artificial intelligence service that analyzes content in images and video.
338 questions
1 answer
Vision API 3.1 read/analyzeResults PDF fails
calling "https://eastus2.api.cognitive.microsoft.com/vision/v3.0/read/analyzeResults?operationId=5d65eed2-d68c-4acd-8f00-6d62dcb852d8" Content-Length: 0 Operation-Location:…
asked 2021-02-12T16:55:25.687+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(3.2, 52%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAD%3C/text%3E%3C/svg%3E)
Ana Del Campo
121
Reputation points Microsoft Employee
commented 2021-02-19T21:34:16.443+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
One of the answers was accepted by the question author.
READ OCR On-Prem Docker Container
I have PDFs that have sensitive information on them and those documents cannot leave our Premises. Does the Docker Container which says it can be deployed on-prem send the pdfs to Microsoft? Thank you
asked 2021-02-12T20:44:05.583+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
accepted 2021-02-16T17:14:19.287+00:00
Baruch Shadrouz
31
Reputation points
1 answer
Unable to find ocr link in computer vision API services.
I've recently subscribed to azure vision API services. I'm able to find subscription key and endpoint but unable to find text recognition (OCR) link. subscription_key = "" endpoint = "" text_recognition_url = endpoint +…
asked 2021-02-15T08:17:32.803+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(144, 72%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ENR%3C/text%3E%3C/svg%3E)
Nithin Reddy
1
Reputation point
commented 2021-02-15T15:11:40.083+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
1 answer
Model behind emotion recogntion
Hi there I'm a psychiatrist in Canada and I'm wondering what model you use for emotion recognition in Azure? Is it based on Open Face or some other validated model? Thank you Paul Waraich
asked 2021-01-27T15:22:40.787+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(163.2, 34%, 25%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EPW%3C/text%3E%3C/svg%3E)
Paul Waraich
1
Reputation point
commented 2021-02-10T17:56:18.433+00:00
Paul Waraich
1
Reputation point
1 answer
Azure Computer Vision Detect Shapes?
Does Azure Computer Vision Detect shapes? I have a whiteboard diagram, and curious if it can determine the overall shapes. I did not see anything in the reference below. …
asked 2021-02-08T02:29:49.48+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(38.4, 40%, 13%)' 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)
AlanSmith4572
6
Reputation points
answered 2021-02-09T05:23:52.407+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
Hot to decrease response time for ReadAPI?
We're using ReadAPI to read some simple labels with little information, the final JSON is about 5kb. The uploaded JPG 100kb. The response time varies between 0,5s (rarely) and 2s, more often around 1s. We check result every 250ms. Result quality…
asked 2021-02-05T16:02:02.953+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, 61%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMD%3C/text%3E%3C/svg%3E)
Mattia Durli
1
Reputation point
answered 2021-02-09T02:12:15.843+00:00
GiftA-MSFT
11,161
Reputation points
2 answers
Computer Vision API 3.0 - Get Read Result
Before getting to development, I thought I'd test the Post Read and Get Read Result via the console API. Successfully received response from all the other computer vision API ( Analyze Image, Describe Image ... ). When trying the same with the Read,…
asked 2020-06-30T08:54:13.467+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, 26%, 38%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EDS%3C/text%3E%3C/svg%3E)
Didrik Skantze
6
Reputation points
answered 2021-02-05T10:06:23.37+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(64, 46%, 16%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ED%3C/text%3E%3C/svg%3E)
Doru
1
Reputation point
0 answers
OCR does not recognize isolated numbers
Whenever I send an image like the attached one, I only get the word REV back but not the number 1 that's under it. More unique number shapes like 2, 3, 4, etc. are usually recognized but the number 1 is rarely recognized.
asked 2020-09-02T05:44:37.777+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(147.20000000000002, 31%, 24%)' 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)
John Saygnavong
1
Reputation point
commented 2021-01-31T16:21:50.72+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(92.8, 63%, 18%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJC%3C/text%3E%3C/svg%3E)
Jim Cantwell
1
Reputation point
2 answers
Azure Computer Vision Cognitive Services - GetReadResultAsync returning duplicated lines when the read document has handwritting and printed text.
I am testing the Azure Computer Vision Cognitive Services with the sample code that the Azure website provides. It works fine when the text is all printed in the image being analyzed, however, when I try to get the results for a mixed document, the…
asked 2021-01-06T20:54:41.18+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(208, 31%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EM%3C/text%3E%3C/svg%3E)
Maie
6
Reputation points
commented 2021-01-28T17:29:38.05+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
About read text and convert
Image: https://prnt.sc/xgxghe I'm trying to detect the image with this name "João Victor". OCR tool showing me on console like in English "Joao Victor" but in process looking for "João Victor". And thats why i cant…
asked 2021-01-22T22:25:23.493+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(86.4, 59%, 18%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EED%3C/text%3E%3C/svg%3E)
Efe Doğanlar
1
Reputation point
answered 2021-01-25T08:16:03.377+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
1 answer
How often Azure Computer Vision is updated ?
Hi, I wonder how often Computer Vision is updated ? I have same image 1 year back, and until today, Computer Vision still not able to identify the person in the image.
asked 2021-01-24T13:19:01.787+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(140.8, 30%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EFC%3C/text%3E%3C/svg%3E)
Frendy Chandra
21
Reputation points
answered 2021-01-25T07:19:36.477+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
1 answer
Azure Conginitve Services Computer Vision
Hi I am wanting to know if there is an on premise version of Azure Computer Vision - without having to hit endpoint of Azure. Strictly on premise with no documents going outside the premises. Thanks
asked 2021-01-12T22:50:53.69+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(208, 7.000000000000001%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EQB%3C/text%3E%3C/svg%3E)
qBotica Bot
6
Reputation points
commented 2021-01-20T06:17:21.827+00:00
YutongTie-MSFT
48,001
Reputation points
1 answer
Read API documentation: How to POST binary data using cURL in PHP?
I got the same problem, I only get words in my response. This is a problem in my case since I will need to get numeric values (partially code). The Read API documentation is really poor and I could not figure out how to send my binary data file using…
asked 2021-01-15T10:45:36.647+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, 46%, 21%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EEK%3C/text%3E%3C/svg%3E)
Ertugrul Kurnaz
1
Reputation point
answered 2021-01-18T08:00:16.097+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
2 answers
One of the answers was accepted by the question author.
Computer Vision API OCR : Not extracting numbers properly
Computer Vision API OCR : Not extracting numbers properly Hey, i am trying to extract the numbers from the attached image but i got the below response,i am calling this from javascript. i am expecting the below response: 0005775 and 0047105 , but i am…
asked 2021-01-11T16:37:07.77+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(70.4, 76%, 16%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EKS%3C/text%3E%3C/svg%3E)
Karthik Somanathan
21
Reputation points
answered 2021-01-15T10:22:23.137+00:00
Ertugrul Kurnaz
1
Reputation point
0 answers
Computer vision returns two the same tags for photo.
Difference only in letter case I guess this is the bug. In me case I got "ferris wheel" with confidence 0.87984049320220947 "Ferris wheel" with confidence 0.61754053831100464 for the same photo
asked 2020-12-24T08:37:28.7+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, 56.00000000000001%, 38%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAM%3C/text%3E%3C/svg%3E)
Alexandr Makhin
1
Reputation point
commented 2020-12-28T11:12:49.067+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
1 answer
Authentication in Azure Vision APIs
Hi, I have few questions regarding authentication process of Azure Vision API with API Key vs AAD. 1) I believe Azure Vision read analyse API has both options for auth - via API key and with AAD? 2) I want to understand for API key vs AAD, which one is…
asked 2020-12-22T16:46:07.887+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(160, 31%, 25%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMG%3C/text%3E%3C/svg%3E)
Mayank Goyal
16
Reputation points
commented 2020-12-24T15:46:38.173+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
1 answer
Azure Computer Vision API
Hi, When we call computer vision API for OCR, we pass image and authentication key via header and get back response. This works great, however I want to check if there is a way to further secure this communication with some certificate and if Yes, how…
asked 2020-10-09T02:08:35.677+00:00
Mayank Goyal
16
Reputation points
commented 2020-12-19T06:17:27.4+00:00
Mayank Goyal
16
Reputation points
1 answer
Extracting data from image using Azure computer vision
Hi, Please suggest if there is a way we can read image left to right and top and bottom with Azure OCR and get result as a single string. We currently get results from image as Json, however if we have to extract values of certain fields from image…
asked 2020-08-24T01:19:11.06+00:00
Mayank Goyal
16
Reputation points
commented 2020-12-19T06:11:33.4+00:00
Mayank Goyal
16
Reputation points
1 answer
Validate Signature In Form Image with Azure Computer Vision
Hi, I have to validate signature in scanned image of form. The aim is not to validate content/name of signature as everyone has different signature. The intent is just to validate if something has been put in box next to signature. I am looking for…
asked 2020-09-25T19:56:47.427+00:00
Mayank Goyal
16
Reputation points
commented 2020-12-14T06:01:11.54+00:00
Ramr-msft
17,651
Reputation points
1 answer
Read API v3.0 not returning angle for PDFs
I've been using v3.0 of the Read API since June 2020. Starting two weeks ago, I noticed that when sending PDFs with multiple pages, the angle returned by the API is always 0, regardless of the orientation of the pages. After converting one of the pages…
asked 2020-11-03T10:24:23.987+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, 84%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJO%3C/text%3E%3C/svg%3E)
João Amaro
1
Reputation point
answered 2020-12-09T19:20:55.41+00:00
GiftA-MSFT
11,161
Reputation points