Back to Documentation

Computer Vision API

Powerful image recognition, object detection, facial analysis, and OCR capabilities powered by cutting-edge deep learning models.

20+ EndpointsIn Development

Overview

Advanced Detection

Detect thousands of objects, faces, and text with high precision

Real-Time Processing

Process images in under 500ms for most operations

Secure & Private

Images are processed and immediately deleted, never stored

Base URL

https://api.wattky.com/v1/vision

Image Input Methods

File Upload

Upload images directly using multipart/form-data

  • • Max file size: 10MB
  • • Formats: JPEG, PNG, GIF, BMP, WebP
  • • Recommended: JPEG for photos, PNG for screenshots

URL Reference

Provide a publicly accessible image URL

  • • Must be publicly accessible
  • • HTTPS recommended
  • • Faster than file upload for large images

Endpoints

POST/v1/vision/analyze

Comprehensive image analysis including objects, scenes, and attributes

Parameters:
image (file or URL)features (optional)
POST/v1/vision/detect-objects

Detect and classify objects with bounding boxes

Parameters:
image (file or URL)confidence_threshold (optional)
POST/v1/vision/detect-faces

Detect faces with landmarks, age, gender, emotions

Parameters:
image (file or URL)include_landmarks (optional)
POST/v1/vision/ocr

Extract text from images with high accuracy

Parameters:
image (file or URL)language (optional)
POST/v1/vision/classify

Classify images into predefined categories

Parameters:
image (file or URL)top_k (optional)
POST/v1/vision/compare

Compare two images for similarity

Parameters:
image1 (file or URL)image2 (file or URL)

Code Examples

cURL

curl -X POST https://api.wattky.com/v1/vision/analyze \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "image=@/path/to/image.jpg" \
  -F "features=objects,faces,text"

Python

import requests

url = "https://api.wattky.com/v1/vision/analyze"
headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

# Using file upload
with open('image.jpg', 'rb') as img:
    files = {'image': img}
    data = {'features': 'objects,faces,text'}
    response = requests.post(url, headers=headers, files=files, data=data)

# Or using image URL
data = {
    'image': 'https://example.com/image.jpg',
    'features': 'objects,faces,text'
}
response = requests.post(url, headers=headers, json=data)

result = response.json()
print(result)

JavaScript

// Using File Upload
const formData = new FormData();
formData.append('image', fileInput.files[0]);
formData.append('features', 'objects,faces,text');

const response = await fetch('https://api.wattky.com/v1/vision/analyze', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: formData
});

// Or using image URL
const response = await fetch('https://api.wattky.com/v1/vision/analyze', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    image: 'https://example.com/image.jpg',
    features: 'objects,faces,text'
  })
});

const result = await response.json();
console.log(result);

Response Format

{
  "status": "success",
  "data": {
    "objects": [
      {
        "label": "person",
        "confidence": 0.98,
        "bounding_box": {
          "x": 120,
          "y": 80,
          "width": 200,
          "height": 350
        }
      },
      {
        "label": "laptop",
        "confidence": 0.94,
        "bounding_box": {
          "x": 250,
          "y": 200,
          "width": 180,
          "height": 120
        }
      }
    ],
    "faces": [
      {
        "confidence": 0.99,
        "age_range": {
          "low": 25,
          "high": 32
        },
        "gender": "female",
        "emotions": {
          "happy": 0.85,
          "neutral": 0.10,
          "surprised": 0.05
        },
        "bounding_box": {
          "x": 145,
          "y": 95,
          "width": 80,
          "height": 100
        }
      }
    ],
    "text": [
      {
        "content": "Hello World",
        "confidence": 0.96,
        "bounding_box": {
          "x": 300,
          "y": 150,
          "width": 120,
          "height": 30
        }
      }
    ],
    "image_properties": {
      "width": 1920,
      "height": 1080,
      "format": "JPEG",
      "dominant_colors": ["#2E3B4E", "#F5F5F5", "#4A90E2"]
    },
    "processing_time_ms": 285
  }
}

Supported Object Categories

Person
Vehicle
Animal
Food
Electronics
Furniture
Clothing
Building
Nature
Sport Equipment
Kitchen Items
Tools
Books
Plants
Signs
Toys

...and 10,000+ individual object types. The model is continuously trained on new categories.

Facial Analysis Features

Attributes

  • Age estimation (range)
  • Gender prediction
  • Emotion detection (7 emotions)
  • Facial landmarks (68 points)

Use Cases

  • User verification systems
  • Emotion-based content filtering
  • Demographics analysis
  • Photo organization tools

Pricing

$0.005
per image analyzed
500ms
average processing time
99.9%
uptime guarantee

Ready to Get Started?

Contact us to get early access to the Computer Vision API and start building intelligent image analysis features into your applications.

Cookie Preferences

We value your privacy

We use cookies and similar technologies to enhance your browsing experience, analyze site traffic, and provide personalized content. By clicking "Accept All", you consent to our use of cookies.

You can customize your preferences or learn more in our Privacy Policy.

GDPR & CCPA Compliant