https://github.com/vikpires/ds_vision-studio-azure
Exploring the capabilities of Vision Studio by Azure AI Services to detect faces, read text OCR, and analyze images.
https://github.com/vikpires/ds_vision-studio-azure
ai ai-900 azure data-science dio-bootcamp vision-studio
Last synced: 6 months ago
JSON representation
Exploring the capabilities of Vision Studio by Azure AI Services to detect faces, read text OCR, and analyze images.
- Host: GitHub
- URL: https://github.com/vikpires/ds_vision-studio-azure
- Owner: vikpires
- License: mit
- Created: 2025-03-09T03:30:30.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-03-16T20:52:52.000Z (7 months ago)
- Last Synced: 2025-03-31T03:32:53.436Z (6 months ago)
- Topics: ai, ai-900, azure, data-science, dio-bootcamp, vision-studio
- Homepage:
- Size: 5.6 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Azure Vision Studio
> Challenge created as part of the Microsoft AI Fundamentals Bootcamp by DIO, based on the tutorials:
- [Detect faces in Vision Studio](https://aka.ms/ai900-face)
- [Read text in Vision Studio](https://aka.ms/ai900-ocr)
- [Analyze images in Vision Studio](https://aka.ms/ai900-image-analysis)
---
## 1. Detect Faces in Vision Studio
### 1.1. Provision an Azure AI services resource
- Start by provisioning an Azure AI services in the Azure portal.
- Search for `Azure AI services` in the Azure portal and create a new Azure AI services resource.
### 1.2. Connect Azure AI service resource to Vision Studio
- Navigate to [Vision Studio](https://portal.vision.cognitive.azure.com).
- On the Getting started with Vision landing page, select the **Face** tab and then select the **Detect Faces** in an image tile.
- Under the Try It Out subheading, acknowledge the resource usage policy by reading and checking the box.
Vision Studio Interface - Detect Faces
### 1.3. Upload the images
The following images can be found in the folder detect-faces.
Image 01
Image 02
Image 03
### 1.4. Output
**Detected Faces - Image 01:**
**Detected Faces - Image 02:**
**Detected Faces - Image 03:**
```
No face detected
```
## 2. Read text in Vision Studio
### 2.1. Navigate to Vision Studio
- Navigate to [Vision Studio](https://portal.vision.cognitive.azure.com).
- On the Getting started with Vision landing page, **Optical character recognition**, and then the **Extract text from images tile**.
- Under the Try It Out subheading, acknowledge the resource usage policy by reading and checking the box.
Vision Studio Interface - OCR
### 2.2. Upload the images
- The following images can be found in the folder read-text-ocr.
Image 01
Image 02
### 2.3. Outputs
**Extracted Text - Image 01:**
```
NorthwindTraders
PIEWINNER
Freshproduce,
friendlyservice
Open7daysaweek
```
**Extracted Text - Image 02:**
```
NorthwindTraders
123MainStreet
555-123-4567
2/17/202013:07
1Apple
$0.90
1Orange
$0.80
Sub-Total
$1.70
Tax
$0.17
Total
$1.87
```
## 3. Analyze images in Visual Studio
### 3.1. Navigate to Vision Studio
- Navigate to [Vision Studio](https://portal.vision.cognitive.azure.com).
- On the Getting started with _Vision_ landing page, **Image analysis**, and then the **Add captions to images**.
- Under the Try It Out subheading, acknowledge the resource usage policy by reading and checking the box.
Vision Studio Interface - Image Analysis
### 3.2. Upload the images
- The following images can be found in the folder analyze-images.
Image 01
Image 02
### 3.3. Output
**Results - Image 01:**
Caption:
```
A woman and a girl in a grocery store
```
JSON attributes generated here.
**Results - Image 02:**
Caption:
```
A woman holding a phone while shopping in a grocery store
```
JSON attributes generated here.