Object Detector API

The Object Detector API is a powerful tool designed to identify objects within images based on specific keywords.

About

Leveraging state-of-the-art machine learning algorithms, this API offers seamless integration for developers seeking to incorporate object detection functionality into their applications.

With the Object Detector API, users can submit images along with a list of keywords corresponding to the objects they wish to identify. The API then processes the image using advanced computer vision techniques to locate and label objects matching the provided keywords. Whether you need to detect common items like "car," "dog," or "tree," or more specialized objects such as "cell phone" or "umbrella," the Object Detector API delivers accurate and reliable results.

Developers can integrate this API into a wide range of applications across various industries, including e-commerce, automotive, healthcare, and more. By accurately identifying objects within images, developers can enhance user experiences, automate tasks, and extract valuable insights from visual data.

Curl Requests and Responses

Process the API

curl -X 'POST' \
  'https://api.magicapi.dev/api/v1/magicapi/objectdetector/objectdetector' \
  -H 'accept: application/json' \
  -H 'x-magicapi-key: API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "image": "https://replicate.delivery/mgxm/36b04aec-efe2-4dea-9c9d-a5faca68b2b2/000000039769.jpg",
  "text": "a photo of a dog | a cat | two cats with remote controls"
}'
{
  "request_id": REQUEST_ID
}

Get the result

curl -X 'GET' \
  'https://api.magicapi.dev/api/v1/magicapi/objectdetector/predictions/REQUEST_ID' \
  -H 'accept: application/json' \
  -H 'x-magicapi-key: API_KEY'
{
  "status": "succeeded",
  "result": [
    3.860912656250548e-8,
    0.0000025217079837602796,
    0.9999974966049194
  ]
}

Last updated