|---| | [ View source on GitHub](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/__init__.py) | MediaPipe Tasks Vision API. ## Modules [`drawing_styles`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/drawing_styles.md.txt) module: MediaPipe solution drawing styles. [`drawing_utils`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/drawing_utils.md.txt) module: MediaPipe solution drawing utils. ## Classes [`class FaceDetector`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceDetector.md.txt): Class that performs face detection on images. [`class FaceDetectorOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceDetectorOptions.md.txt): Options for the face detector task. [`class FaceDetectorResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceDetectorResult.md.txt): Represents the list of detected objects. [`class FaceLandmarker`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceLandmarker.md.txt): Class that performs face landmark detection on images. [`class FaceLandmarkerOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceLandmarkerOptions.md.txt): Options for the face landmarker task. [`class FaceLandmarkerResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceLandmarkerResult.md.txt): The face landmarks detection result from FaceLandmarker, where each vector element represents a single face detected in the image. [`class FaceLandmarksConnections`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/FaceLandmarksConnections.md.txt): The connections between face landmarks. [`class GestureRecognizer`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/GestureRecognizer.md.txt): Class that performs gesture recognition on images. [`class GestureRecognizerOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/GestureRecognizerOptions.md.txt): Options for the gesture recognizer task. [`class GestureRecognizerResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/GestureRecognizerResult.md.txt): The gesture recognition result from GestureRecognizer. [`class HandLandmarker`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HandLandmarker.md.txt): Class that performs hand landmarks detection on images. [`class HandLandmarkerOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HandLandmarkerOptions.md.txt): Options for the hand landmarker task. [`class HandLandmarkerResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HandLandmarkerResult.md.txt): The hand landmarks result from HandLandmarker, where each vector element represents a single hand detected in the image. [`class HandLandmarksConnections`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HandLandmarksConnections.md.txt): The connections between hand landmarks. [`class HolisticLandmarker`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HolisticLandmarker.md.txt): Class that performs holistic landmarks detection on images. [`class HolisticLandmarkerOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HolisticLandmarkerOptions.md.txt): Options for the holistic landmarker task. [`class HolisticLandmarkerResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/HolisticLandmarkerResult.md.txt): The holistic landmarks result from HolisticLandmarker, where each vector element represents a single holistic detected in the image. [`class ImageClassifier`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageClassifier.md.txt): Class that performs image classification on images. [`class ImageClassifierOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageClassifierOptions.md.txt): Options for the image classifier task. [`class ImageClassifierResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageClassifierResult.md.txt): Contains the classification results of a model. [`class ImageEmbedder`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageEmbedder.md.txt): Class that performs embedding extraction on images. [`class ImageEmbedderOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageEmbedderOptions.md.txt): Options for the image embedder task. [`class ImageEmbedderResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageEmbedderResult.md.txt): Embedding results for a given embedder model. [`class ImageProcessingOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageProcessingOptions.md.txt): Options for image processing. [`class ImageSegmenter`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageSegmenter.md.txt): Class that performs image segmentation on images. [`class ImageSegmenterOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageSegmenterOptions.md.txt): Options for the image segmenter task. [`class InteractiveSegmenter`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenter.md.txt): A task to perform interactive segmentation on images. [`class InteractiveSegmenterBrushMode`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterBrushMode.md.txt): The brush mode for interactive segmentation. [`class InteractiveSegmenterLegacy`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterLegacy.md.txt): Class that performs interactive segmentation on images. [`class InteractiveSegmenterLegacyOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterLegacyOptions.md.txt): Options for the interactive segmenter task. [`class InteractiveSegmenterLegacyRegionOfInterest`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterLegacyRegionOfInterest.md.txt): The Region-Of-Interest (ROI) to interact with. [`class InteractiveSegmenterOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterOptions.md.txt): Options for the interactive segmenter task. [`class InteractiveSegmenterStroke`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterStroke.md.txt): A stroke representing user interaction for segmentation. [`class InteractiveSegmenterStrokePoint`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/InteractiveSegmenterStrokePoint.md.txt): A single 2D point in a stroke. [`class ObjectDetector`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ObjectDetector.md.txt): Class that performs object detection on images. [`class ObjectDetectorOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ObjectDetectorOptions.md.txt): Options for the object detector task. [`class ObjectDetectorResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ObjectDetectorResult.md.txt): Represents the list of detected objects. [`class PoseLandmark`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmark.md.txt): The 33 pose landmarks. [`class PoseLandmarker`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarker.md.txt): Class that performs pose landmarks detection on images. [`class PoseLandmarkerOptions`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarkerOptions.md.txt): Options for the pose landmarker task. [`class PoseLandmarkerResult`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarkerResult.md.txt): The pose landmarks detection result from PoseLandmarker, where each vector element represents a single pose detected in the image. [`class PoseLandmarksConnections`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarksConnections.md.txt): The connections between pose landmarks. [`class RunningMode`](https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/RunningMode.md.txt): MediaPipe vision task running mode.