pyflink.multimodal.expression.ImageExpressionAccessor.face_detect

ImageExpressionAccessor.face_detect(*, cv_classifier: str = 'haarcascade_frontalface_alt.xml', min_neighbors: int = 3, scale_factor: float = 1.1, min_size: Optional[Union[List[int], Tuple[int, int]]] = None, max_size: Optional[Union[List[int], Tuple[int, int]]] = None, concurrency: Optional[int] = None) → pyflink.table.expression.Expression

Detect faces in image values.

Equivalent to image_face_detect(). See that function for full parameter details.

Parameters

• cv_classifier – OpenCV cascade classifier file name.

• min_neighbors – Minimum neighbor count for face detection.

• scale_factor – Scale factor used by the detector pyramid.

• min_size – Optional minimum face size.

• max_size – Optional maximum face size.

• concurrency – Optional execution concurrency for this operation. None uses the framework default.

Returns

A DataFrame expression that produces ARRAY<ROW> face detections with x, y, w, h, and confidence fields.