Object Recognition API Reference

This section provides a comprehensive guide to the Object Recognition API, which allows users to detect and identify objects within images.

Features

• Real-time Detection: The API provides real-time object detection capabilities.
• High Accuracy: Achieves high accuracy in object recognition.
• Supports Multiple Languages: The API supports multiple languages, including English and Chinese.

Usage

To use the Object Recognition API, you need to send an HTTP GET request to the following endpoint:

GET /ai_toolkit/en/docs/api_reference/object_recognition

Example Request

GET /ai_toolkit/en/docs/api_reference/object_recognition?image_url=https://example.com/image.jpg

Response

The API returns a JSON object with the following fields:

• objects: An array of detected objects, each with the following fields:
  • name: The name of the object.
  • confidence: The confidence level of the detection.
  • bounding_box: The bounding box coordinates of the object.
• status: The status of the API call.

Example Response

{
  "objects": [
    {
      "name": "cat",
      "confidence": 0.95,
      "bounding_box": [10, 20, 100, 100]
    },
    {
      "name": "dog",
      "confidence": 0.85,
      "bounding_box": [200, 300, 150, 150]
    }
  ],
  "status": "success"
}

Further Reading

For more detailed information, please refer to the Object Recognition API documentation.

图片示例

Here is an example of a detected object:

For more examples, please visit our gallery.