> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/MicrosoftDocs/azure-ai-docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Computer Vision Overview

> Extract visual features from images including OCR, object detection, image analysis, and caption generation

# Computer Vision (Image Analysis)

Azure Computer Vision provides AI algorithms for processing images and extracting visual information. The Image Analysis service uses pre-trained models to analyze images and return insights about visual features and characteristics.

## Key Capabilities

The Image Analysis API provides comprehensive image understanding features:

<CardGroup cols={2}>
  <Card title="OCR (Read Text)" icon="font">
    Extract printed and handwritten text from images with high accuracy
  </Card>

  <Card title="Object Detection" icon="square-check">
    Detect and locate objects in images with bounding boxes and confidence scores
  </Card>

  <Card title="Image Captioning" icon="message">
    Generate human-readable descriptions of image content in complete sentences
  </Card>

  <Card title="People Detection" icon="users">
    Detect people in images and return bounding box coordinates for each person
  </Card>

  <Card title="Visual Tagging" icon="tags">
    Identify and tag thousands of recognizable objects, living things, scenery, and actions
  </Card>

  <Card title="Smart Cropping" icon="crop">
    Determine the area of interest in images to create optimal thumbnails
  </Card>
</CardGroup>

## Image Analysis Features

### Read Text from Images (OCR)

Version 4.0 offers synchronous OCR capabilities that extract text from images:

* Extract printed and handwritten text
* Support for multiple languages
* High accuracy text recognition
* Faster performance than async Read API
* Returns text with bounding box coordinates

```python theme={null}
from azure.ai.vision.imageanalysis import ImageAnalysisClient
from azure.core.credentials import AzureKeyCredential

client = ImageAnalysisClient(
    endpoint="https://<your-resource>.cognitiveservices.azure.com/",
    credential=AzureKeyCredential("<your-key>")
)

result = client.analyze_from_url(
    image_url="https://example.com/image.jpg",
    visual_features=["READ"]
)

for block in result.read.blocks:
    for line in block.lines:
        print(f"Text: {line.text}")
```

### Generate Image Captions

Create human-readable descriptions of images:

* **Simple captions**: One-sentence descriptions of the entire image
* **Dense captions**: Detailed captions for individual objects with bounding boxes
* Natural language descriptions
* High accuracy based on image content

```python theme={null}
result = client.analyze_from_url(
    image_url="https://example.com/image.jpg",
    visual_features=["CAPTION"]
)

print(f"Caption: {result.caption.text}")
print(f"Confidence: {result.caption.confidence}")
```

### Detect Objects

Identify objects in images with bounding boxes:

* Detect multiple instances of the same object
* Return pixel coordinates for each object
* Confidence scores for each detection
* Support for thousands of object categories

```python theme={null}
result = client.analyze_from_url(
    image_url="https://example.com/image.jpg",
    visual_features=["OBJECTS"]
)

for obj in result.objects:
    print(f"Object: {obj.tags[0].name}")
    print(f"Confidence: {obj.tags[0].confidence}")
    print(f"Bounding box: {obj.bounding_box}")
```

### People Detection

Detect people appearing in images (v4.0 only):

* Returns bounding box coordinates for each person
* Confidence scores for each detection
* Works with single or multiple people

```python theme={null}
result = client.analyze_from_url(
    image_url="https://example.com/image.jpg",
    visual_features=["PEOPLE"]
)

for person in result.people:
    print(f"Person detected at: {person.bounding_box}")
    print(f"Confidence: {person.confidence}")
```

### Tag Visual Features

Identify and tag visual content:

* Thousands of recognizable objects, living things, scenery, and actions
* Tags with confidence scores
* Context hints for ambiguous tags
* Includes both main subjects and background elements

```python theme={null}
result = client.analyze_from_url(
    image_url="https://example.com/image.jpg",
    visual_features=["TAGS"]
)

for tag in result.tags:
    print(f"{tag.name}: {tag.confidence}")
```

### Smart Cropping (Area of Interest)

Find the optimal region of interest for thumbnails:

* Analyzes image content to determine focus area
* Returns bounding box coordinates
* Supports custom aspect ratios
* Preserves the most important visual elements

```python theme={null}
result = client.analyze_from_url(
    image_url="https://example.com/image.jpg",
    visual_features=["SMART_CROPS"],
    smart_crops_aspect_ratios=[0.9, 1.33]
)

for crop in result.smart_crops:
    print(f"Crop box: {crop.bounding_box}")
```

## Additional Features (v3.2)

Version 3.2 includes these additional capabilities:

* **Brand Detection**: Identify commercial brands and logos
* **Face Detection**: Detect faces and estimate age and gender
* **Image Type Detection**: Determine if image is clip art or line drawing
* **Color Scheme Detection**: Identify dominant and accent colors
* **Adult Content Detection**: Detect adult, racy, or gory content
* **Domain-Specific Models**: Detect celebrities and landmarks
* **Image Categorization**: Categorize images using a taxonomy

## Multimodal Embeddings

Convert images and text to vector representations for semantic search:

* Vectorize images for similarity search
* Convert text queries to vectors
* Match images to text based on semantic meaning
* Support for 102 languages (multilingual model)
* Build image search applications

```python theme={null}
from azure.ai.vision.imageanalysis import VectorizeClient

vectorize_client = VectorizeClient(
    endpoint="https://<your-resource>.cognitiveservices.azure.com/",
    credential=AzureKeyCredential("<your-key>")
)

# Vectorize an image
image_vector = vectorize_client.vectorize_image(
    image_url="https://example.com/image.jpg"
)

# Vectorize a text query
text_vector = vectorize_client.vectorize_text(
    text="a dog playing in the park"
)
```

## API Versions

### Version 4.0 (Recommended)

* Synchronous OCR (Read)
* People detection
* Dense captions
* Enhanced image captioning
* Improved smart cropping
* Multimodal embeddings

### Version 3.2

* Async OCR (Read API)
* Brand detection
* Face detection
* Celebrity and landmark detection
* All other v3.2 features

## Input Requirements

**Version 4.0:**

* Supported formats: JPEG, PNG, GIF, BMP, WEBP, ICO, TIFF, MPO
* File size: Less than 20 MB
* Dimensions: 50 x 50 to 16,000 x 16,000 pixels

**Version 3.2:**

* Supported formats: JPEG, PNG, GIF, BMP
* File size: Less than 4 MB
* Dimensions: 50 x 50 to 16,000 x 16,000 pixels

## Region Availability

| Region         | Analyze Image | Captions (v4.0) | Embeddings |
| -------------- | ------------- | --------------- | ---------- |
| East US        | ✓             | ✓               | ✓          |
| West US        | ✓             | ✓               | ✓          |
| West US 2      | ✓             |                 | ✓          |
| North Europe   | ✓             | ✓               | ✓          |
| West Europe    | ✓             | ✓               | ✓          |
| Southeast Asia | ✓             | ✓               | ✓          |

## Use Cases

<AccordionGroup>
  <Accordion title="Content Moderation">
    * Detect inappropriate images
    * Filter adult content
    * Ensure brand safety
    * Monitor user-generated content
  </Accordion>

  <Accordion title="E-commerce">
    * Generate product descriptions
    * Tag products automatically
    * Create smart thumbnails
    * Enable visual search
  </Accordion>

  <Accordion title="Accessibility">
    * Generate alt text for images
    * Read text aloud from images
    * Describe visual content
    * Support screen readers
  </Accordion>

  <Accordion title="Document Processing">
    * Extract text from scanned documents
    * Digitize printed materials
    * Process forms and receipts
    * Archive historical documents
  </Accordion>
</AccordionGroup>

## Getting Started

<Steps>
  <Step title="Create Computer Vision Resource">
    Create an Azure Computer Vision resource in the Azure Portal
  </Step>

  <Step title="Get Credentials">
    Retrieve your endpoint URL and API key from the resource
  </Step>

  <Step title="Install SDK">
    Install the Computer Vision SDK for your preferred language:

    ```bash theme={null}
    pip install azure-ai-vision-imageanalysis
    ```
  </Step>

  <Step title="Analyze Images">
    Use the SDK to analyze images and extract features
  </Step>
</Steps>

## SDK Support

<CardGroup cols={2}>
  <Card title="Python" icon="python">
    ```bash theme={null}
    pip install azure-ai-vision-imageanalysis
    ```
  </Card>

  <Card title="C#" icon="c">
    ```bash theme={null}
    dotnet add package Azure.AI.Vision.ImageAnalysis
    ```
  </Card>

  <Card title="Java" icon="java">
    ```xml theme={null}
    <dependency>
      <groupId>com.azure</groupId>
      <artifactId>azure-ai-vision-imageanalysis</artifactId>
    </dependency>
    ```
  </Card>

  <Card title="JavaScript" icon="js">
    ```bash theme={null}
    npm install @azure-rest/ai-vision-image-analysis
    ```
  </Card>
</CardGroup>

## Pricing

* **Free Tier (F0)**: 5,000 transactions per month
* **Standard Tier (S1)**: Pay per 1,000 transactions
* Different pricing for v3.2 and v4.0 features
* Additional costs for custom models

## Next Steps

* [Try Vision Studio](https://portal.vision.cognitive.azure.com/)
* [View Image Analysis Quickstart](https://learn.microsoft.com/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library-40)
* [Explore Code Samples](https://github.com/Azure-Samples/azure-ai-vision-sdk)
* [Learn about Custom Vision](/ai-services/custom-vision/overview)