OFR: Optical Feature Recognition

Our API provides a feature to extract visual features from images.

Identify visual features in images.

Performs optical feature recognition (OFR) to identify visual features such as objects, landmarks, or logos from images, aiding in image analysis and categorization.

POSThttps://api.aimlapi.com/vision

Body

application/json

image*VisionRequestImageDTO (object)

features*array of VisionFeatureDTO (object)

imageContextVisionImageContextDTO (object)

Response

201

Body

application/json

faceAnnotationsnullable array of nullable any

landmarkAnnotationsnullable array of nullable any

logoAnnotationsnullable array of nullable any

labelAnnotationsnullable array of nullable any

localizedObjectAnnotationsnullable array of nullable any

textAnnotationsnullable array of nullable any

fullTextAnnotationnullable any

safeSearchAnnotationnullable any

imagePropertiesAnnotationnullable any

cropHintsAnnotationnullable any

webDetectionnullable any

productSearchResultsnullable any

errornullable any

contextnullable any

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/vision', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "image": {
        "source": {
          "imageUri": "text"
        }
      },
      "features": [
        {
          "type": "FACE_DETECTION"
        }
      ]
    }),
});
const data = await response.json();

Response

201

{
  "faceAnnotations": [],
  "landmarkAnnotations": [],
  "logoAnnotations": [],
  "labelAnnotations": [],
  "localizedObjectAnnotations": [],
  "textAnnotations": []
}