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.
How do we help/increase the reading accuracy "train the OCR AI to read better letters and numbers" better
using the Azure AI OCR to read numbers and letters that has been stanched on Plates increase the accuracy of the AI OCR to read punched numbers and letters on a plate, is there anyway i can do this? or do i in that case have to train my own. My…
asked 2024-05-24T12:48:07.37+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(118.4, 8%, 21%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJG%3C/text%3E%3C/svg%3E)
Johan Ögren
20
Reputation points
accepted 2024-05-27T05:57:59.1833333+00:00
Johan Ögren
20
Reputation points
0 answers
Azure Computer Vision - custom Image Analysis Rest API - create dataset - blob container not available
Hi, When using the Rest API curl command to create a training dataset on Azure Custom Vision - Vision Studio - for custom Image Analysis, it says blob container not available on the studio portal, although the dataset is created successfully. See…
asked 2024-05-23T09:24:18.18+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(252.8, 4%, 34%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ECL%3C/text%3E%3C/svg%3E)
Clodagh Lynch
50
Reputation points Microsoft Employee
commented 2024-05-27T01:51:32.1533333+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(89.60000000000001, 78%, 18%)' 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)
dupammi
7,955
Reputation points Microsoft Vendor
1 answer
Can I use a different region for a azure resource if I am in another region ?
I am making a new computer vision resource, at first I set the region to central India and my program threw an error of "Captions function is not present in my region". So, I checked and found the captions function in image analysis is present…
asked 2024-05-22T12:43:23.22+00:00
Arpit Nayak
0
Reputation points
edited an answer 2024-05-23T12:56:20.5633333+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
1 answer
Vision AI Dev Kit Unable to Upgrade Firmware - Error < waiting for any device >
Good Day All. Please help me I received my new camera today and I am not having any luck Vision AI Dev Kit Unable to Upgrade Firmware - Error < waiting for any device >
asked 2024-05-22T18:53:26.8566667+00:00
Arno Moolman
0
Reputation points
edited an answer 2024-05-23T05:33:54.37+00:00
dupammi
7,955
Reputation points Microsoft Vendor
1 answer
One of the answers was accepted by the question author.
Azure Vision OCR - Offline
I tried to ask this simple question using the Azure Chat bot but it sent me to support requests and it appear simple questions cannot be asked there. My question is: Can Azure Vision OCR be configured as an offline service using IoT Edge or similar?
asked 2024-05-17T00:08:08.77+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(240, 28.000000000000004%, 33%)' 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)
Richard Smith
20
Reputation points
accepted 2024-05-22T05:30:18.12+00:00
Richard Smith
20
Reputation points
1 answer
One of the answers was accepted by the question author.
Is Image caption and dense caption going to be supported in data center Australia?
Is Image caption and dense caption going to be supported in data center Australia in the near future and if so is there a timeline for this. Thanks.
![](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(316.8, 82%, 40%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJ%3C/text%3E%3C/svg%3E)
1 answer
Vision Studio - Add Captions to Images - "Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource."
I have a free tier subscription (created my azure a/c a week ago). I created a resource 5 minutes ago (under the only resource group I have) and I am trying the "add captions to images" feature under Vision Studio using an image provided in the…
asked 2024-05-16T11:33:25.5966667+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(272, 52%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ES7%3C/text%3E%3C/svg%3E)
SoumyaY-7595
20
Reputation points
commented 2024-05-16T15:38:28.2366667+00:00
SoumyaY-7595
20
Reputation points
1 answer
I want to use Document Intelligent 2023-10-31-preview read as on-premise container
Hello MS team, I want to use the Document Intelligence 2023-10-31-preview as on-premises container. Can you provide it now as a docker container and if not what are other alternatives that can recognize Arabic handwritten text?
asked 2024-05-14T13:28:47.1366667+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(188.79999999999998, 59%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EB%3C/text%3E%3C/svg%3E)
bushr
25
Reputation points
answered 2024-05-14T16:36:00.1566667+00:00
romungi-MSFT
43,656
Reputation points Microsoft Employee
0 answers
What is the best Azure tool for human detection on Hololens2?
I want to do human detection on Hololens2, is Computer Vision video analytics the best Azure tool to implement? I need to get the coordinates of a person on Hololens2 for my university research.
![](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(246.4, 84%, 33%)' 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)
0 answers
Extracting quality square crops of images from non-square images
I need to automatically extract quality square thumbnails from non-square images. By 'quality', I mean what most people would recognize as being a good crop. I'm particularly interested in processing images of animals and plants. e.g. if you take this…
asked 2024-05-07T10:42:33.6033333+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(48, 33%, 14%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EDE%3C/text%3E%3C/svg%3E)
David Ebbo
5
Reputation points
commented 2024-05-09T11:43:07.36+00:00
David Ebbo
5
Reputation points
1 answer
One of the answers was accepted by the question author.
Try it out
Following the guide (https://video2.skills-academy.com/en-us/azure/ai-services/computer-vision/how-to/model-customization?tabs=studio) and having succeeded to the point of model training and evaluation. Now i want to try / test the one. But i don't have the…
asked 2024-05-06T06:54:45.09+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(281.6, 81%, 37%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAZ%3C/text%3E%3C/svg%3E)
Alexey Zhilenko
20
Reputation points
accepted 2024-05-08T15:24:15.35+00:00
Alexey Zhilenko
20
Reputation points
0 answers
How to improve accuracy of OCR?
Hello, is there any way to label and train data in the custom model without manually updating ocr.json and label.json . I'm currently facing issue with these characters, Character having high failure frequency: - 1 (as I, J and T), 5 (as S), D (as 0 and…
asked 2024-05-06T18:10:54.43+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(259.20000000000005, 5%, 35%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAS%3C/text%3E%3C/svg%3E)
Anurag Singh
0
Reputation points
commented 2024-05-08T05:51:56.0433333+00:00
Anurag Singh
0
Reputation points
2 answers
One of the answers was accepted by the question author.
Vision API AnnotationUrls and AuthenticationKind not uploading COCO file
Getting error message: "message": "AuthenticationKind is required for registering dataset using AnnotationFileUrls." when using Azure Vision AI API. This is the curl command I'm using curl.exe -v -X PUT…
asked 2024-05-02T13:50:17.3266667+00:00
Clodagh Lynch
50
Reputation points Microsoft Employee
answered 2024-05-02T16:06:41.9233333+00:00
Charlie Wei
3,310
Reputation points
0 answers
OCR Language support for Greek, Hebrew, Thai, Vietnamese
Hello! I have a question regarding the OCR language support for print text. https://video2.skills-academy.com/en-us/azure/cognitive-services/computer-vision/language-support#print-text These languages aren't supported at this point: Greek Hebrew Thai …
asked 2023-04-14T14:29:34.7133333+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(272, 71%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMS%3C/text%3E%3C/svg%3E)
Maciej Szulc
5
Reputation points
commented 2024-05-02T06:35:10.3166667+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(108.80000000000001, 24%, 20%)' 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)
AZ
0
Reputation points
0 answers
Unable to use pretrained model in AI vision studio
Hi ive been trying to use the pretrained model for object detection use case, have created a resource for it as well. It still wont work, and i get the error "Resource not found". Ive utilized this source via python sdk as well, and it was…
asked 2024-04-23T11:21:41.7933333+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(233.6, 7.000000000000001%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ERK%3C/text%3E%3C/svg%3E)
Rishi Khemka
60
Reputation points
edited a comment 2024-04-29T19:32:04.05+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(195.2, 4%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EVM%3C/text%3E%3C/svg%3E)
VasaviLankipalle-MSFT
15,836
Reputation points
0 answers
Python SDK for Product detection on shelf using Computer Vision and custom vision.
Hi im unable to find the correct documentation for product detection on shelf, using both computer vision and also using custom vision. I want to know whether a documentation exists outlining all functions and parameters that go into each function using…
asked 2024-04-24T08:07:48.6233333+00:00
Rishi Khemka
60
Reputation points
edited a comment 2024-04-26T08:47:45.79+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' %3ES%3C/text%3E%3C/svg%3E)
santoshkc
6,310
Reputation points Microsoft Vendor
1 answer
Which vision ai model is suitable for reading and extracting data from a graph (bar, line or combined) ?
I am working on a project where I am attempting to use an AI model to read graphs accurately and extract data from them. I have tried many models, but the accuracy is low. What about Azure Computer Vision and Custom Vision? Do they have this capability?
asked 2024-04-24T17:26:20.85+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, 99%, 38%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAS%3C/text%3E%3C/svg%3E)
Avinash Shrivastava
0
Reputation points
edited an answer 2024-04-24T22:48:32.55+00:00
VasaviLankipalle-MSFT
15,836
Reputation points
1 answer
I keep getting this error {"errorCode":"BadRequestInvalidResourceId","properties":null} whenever i try to upload an image to computer vision for its captioning
I keep getting this error {"errorCode":"BadRequestInvalidResourceId","properties":null} whenever i try to upload an image to computer vision for its captioning, even the sample images throw the same error
asked 2024-04-24T09:37:33.5133333+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(28.799999999999997, 28.999999999999996%, 12%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESJ%3C/text%3E%3C/svg%3E)
Shubham Jain
0
Reputation points
answered 2024-04-24T19:44:29.1066667+00:00
VasaviLankipalle-MSFT
15,836
Reputation points
1 answer
One of the answers was accepted by the question author.
Product detection API from Custom Vision & Computer Vision
I want to use product detection api from custom vision and computer vision, here are few questions i have on them 1- Say we train the model to identify X magazine based on a set of images, now after we want to do prediction the version of magazine X…
asked 2024-04-24T08:03:19.98+00:00
Rishi Khemka
60
Reputation points
accepted 2024-04-24T11:19:57.8633333+00:00
Rishi Khemka
60
Reputation points
1 answer
One of the answers was accepted by the question author.
Azure AI Vision Studio OCR cannot read PDF files
I am trying to read PDF files using Azure Vision Studio and despite the tool telling me it can extract text from PDF files I get an error. I have tried multiple types of PDF files; multi-page, single page as well as PDF's that are essentially scanned…
asked 2024-04-20T10:57:34.8766667+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(217.60000000000002, 67%, 31%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EI%3C/text%3E%3C/svg%3E)
IanCodeAce
30
Reputation points
edited the question 2024-04-23T16:25:59.1933333+00:00
VasaviLankipalle-MSFT
15,836
Reputation points