detectFacesFromCameraImage method

Future<List<Face>> detectFacesFromCameraImage(
  1. Object cameraImage, {
  2. FaceDetectionMode mode = FaceDetectionMode.full,
  3. CameraFrameRotation? rotation,
  4. bool? isBgra,
  5. int? maxDim,
})

One-call wrapper for live camera streams: takes a CameraImage-shaped object directly (any object exposing width, height, and planes with bytes / bytesPerRow / bytesPerPixel) and runs YUV packing, colour conversion, rotation, and downscale in the detection isolate - all off the UI thread.

Returns an empty list (not an error) when the plane shape can't be decoded. Throws at runtime if cameraImage doesn't expose the expected shape.

isBgra selects BGRA vs. RGBA for the desktop single-plane path; ignored for YUV input (Android/iOS). Defaults to true on macOS (BGRA) and false on Windows/Linux (RGBA). Only pass this explicitly if you are using a non-standard camera plugin that delivers a different format.

Throws StateError if initialize has not been called successfully.

Implementation

Future<List<Face>> detectFacesFromCameraImage(
  Object cameraImage, {
  FaceDetectionMode mode = FaceDetectionMode.full,
  CameraFrameRotation? rotation,
  bool? isBgra,
  int? maxDim,
}) async {
  _requireReady();
  final frame = prepareCameraFrameFromImage(
    cameraImage,
    rotation: rotation,
    isBgra: isBgra ?? Platform.isMacOS,
  );
  if (frame == null) return const <Face>[];
  return detectFacesFromCameraFrame(frame, mode: mode, maxDim: maxDim);
}