|
import face_recognition image = face_recognition.load_image_file("photo.jpg") face_locations = face_recognition.face_locations(image) # Returns array of face bounds face_encodings = face_recognition.face_encodings(image) # Returns array of face vectors content = { "locations": face_locations, # Array of (top, right, bottom, left) "encodings": face_encodings # Array of 128D arrays } Some APIs return detection results as:
face_array = [ [0.12, -0.34, 0.56, ...], # Face encoding 1 [0.45, 0.21, -0.78, ...] # Face encoding 2 ] content = {"faces": face_array} In face recognition libraries (like face_recognition in Python or dlib ), you often get a face array — an array of bounding boxes or 128-dimensional face encodings. face array
{ "content": [ { "face_id": 1, "bounds": [100, 150, 200, 200], "landmarks": [ ... ] }, { "face_id": 2, "bounds": [300, 120, 190, 190], "landmarks": [ ... ] } ] } import face_recognition image = face_recognition
Here are the most likely meanings depending on your context: You might be describing a data object where the content key holds an array (list) of faces (e.g., detected faces from an image, or a list of face objects). ] } ] } Here are the most