API Reference

init_sdk

def init_sdk() -> int:

Name	init_sdk
Description	Initializes the SDK.
Input	None
Output	Status code indicating the result of the initialization. 0: Success Non-zero: Initialization failed

get_attribute

def get_attribute(image: np.ndarray, width: int, height: int, face_results: ctypes.POINTER(FaceResult), max_face_num: int, mode: int) -> int:

Name	get_attribute
Description	Detects and analyzes face.
Input	image (numpy.ndarray): Input image matrix width (int): Width of the input image height (int): Height of the input image face_results (ctypes.POINTER): Pointer to a structure containing face results max_face_num (int): Maximum number of faces to detect mode (int): 0-> Enroll mode, 1-> Identify mode
Output	Status code indicating the result of getting attribute. >0: Number of detected faces 0: No Face otherwise: Error

Here is FaceResult Structure.

class FaceResult(Structure):
    _fields_ = [
        ("x1", c_int32),
        ("y1", c_int32),
        ("x2", c_int32),
        ("y2", c_int32),
        ("liveness", c_int32),
        ("mask", c_int32),
        ("glass", c_int32),
        ("age", c_int32),
        ("gender", c_int32),
        ("feature", c_ubyte * 2056)
    ]

(x1, y1)	Coordinate of the top-left corner of the bounding box of the detected face.
(x2, y2)	Coordinate of the bottom-right corner of the bounding box of the detected face.
liveness	Liveness score of detected face 0 -> SPOOF 1 -> REAL -3 -> TOO SMALL FACE -4 -> TOO LARGE FACE -102 -> NO FACE -103 -> LIVENESS CHECK FAILED
mask	Mask detection of the detected face 0 -> No, 1 -> Yes
glass	Glass detection of the detected face 0 -> No, 1 -> Yes
age	Estimated age of the detected face
gender	Gender prediction of the detected face 0 -> Male, 1 -> Female
feature	Template buffer. Extracted template will be stored

calculate_similarity

def calculate_similarity(feature_1: np.ndarray, feature_2: np.ndarray) -> float:

Name	calculate_similarity
Description	Calculates the similarity between two features
Input	feature_1 (numpy.ndarray): 1st feature feature_2 (numpy.ndarray): 2nd feature
Output	Similarity score between the two features The score ranges from 0.0 to 1.0 Default Threshold is 0.82