Attention: This MediaPipe Solutions Preview is an early release. Learn more.


Stay organized with collections Save and categorize content based on your preferences.

MediaPipe Tasks Vision API.


class GestureRecognizer: Class that performs gesture recognition on images.

class GestureRecognizerOptions: Options for the gesture recognizer task.

class GestureRecognizerResult: The gesture recognition result from GestureRecognizer, where each vector element represents a single hand detected in the image.

class HandLandmarker: Class that performs hand landmarks detection on images.

class HandLandmarkerOptions: Options for the hand landmarker task.

class HandLandmarkerResult: The hand landmarks result from HandLandmarker, where each vector element represents a single hand detected in the image.

class ImageClassifier: Class that performs image classification on images.

class ImageClassifierOptions: Options for the image classifier task.

class ImageClassifierResult: Contains the classification results of a model.

class ImageEmbedder: Class that performs embedding extraction on images.

class ImageEmbedderOptions: Options for the image embedder task.

class ImageEmbedderResult: Embedding results for a given embedder model.

class ImageSegmenter: Class that performs image segmentation on images.

class ImageSegmenterOptions: Options for the image segmenter task.

class ObjectDetector: Class that performs object detection on images.

class ObjectDetectorOptions: Options for the object detector task.

class RunningMode: MediaPipe vision task running mode.