Image segmentation guide for Python

The MediaPipe Image Segmenter task lets you divide images into regions based on predefined categories for applying visual effects such as background blurring. These instructions show you how to use the Image Segmenter with the Python language. For more information about the capabilities, models, and configuration options of this task, see the Overview.

Code example

The example code for Image Segmenter provides a complete implementation of this task in Python for your reference. This code helps you test this task and get started on building your own image segmenter application. You can view, run, and edit the Image Segmenter example code using just your web browser.

Setup

This section describes key steps for setting up your development environment and code projects specifically to use Image Segmenter. For general information on setting up your development environment for using MediaPipe tasks, including platform version requirements, see the Setup guide for Python. You can review the source code for this example on GitHub

Packages

The MediaPipe Image Segmenter task requires the mediapipe package. You can install the required dependencies with the following command:

$ python -m pip install mediapipe

Imports

Import the following classes to access the Image Segmenter task functions:

import mediapipe as mp
from mediapipe.tasks import python
from mediapipe.tasks.python import vision

Model

The MediaPipe Image Segmenter task requires a trained model that is compatible with this task. For more information on available trained models for Image Segmenter, see the task overview Models section.

Select and download the model, and then store it within your project directory:

model_path = '/absolute/path/to/model.tflite'

Specify the path of the model within the Model Name parameter, as shown below:

base_options = BaseOptions(model_asset_path=model_path)

Create the task

The MediaPipe Image Segmenter task uses the create_from_options function to set up the task. The create_from_options function accepts values for configuration options to handle. For more information on task configuration, see Configuration options.

These samples also show the variations of the task construction for images, video files, and live video streams.

BaseOptions = mp.tasks.BaseOptions
ImageSegmenter = mp.tasks.vision.ImageSegmenter
ImageSegmenterOptions = mp.tasks.vision.ImageSegmenterOptions
VisionRunningMode = mp.tasks.vision.RunningMode

# Create a image segmenter instance with the image mode:
options = ImageSegmenterOptions(
    base_options=BaseOptions(model_asset_path='/path/to/model.task'),
    running_mode=VisionRunningMode.IMAGE,
    output_category_mask=True)
with ImageSegmenter.create_from_options(options) as segmenter:
  

BaseOptions = mp.tasks.BaseOptions
ImageSegmenter = mp.tasks.vision.ImageSegmenter
ImageSegmenterOptions = mp.tasks.vision.ImageSegmenterOptions
VisionRunningMode = mp.tasks.vision.RunningMode

# Create a image segmenter instance with the video mode:
options = ImageSegmenterOptions(
    base_options=BaseOptions(model_asset_path='/path/to/model.task'),
    running_mode=VisionRunningMode.VIDEO,
    output_category_mask=True)
with ImageSegmenter.create_from_options(options) as segmenter:
  

BaseOptions = mp.tasks.BaseOptions
ImageSegmenter = mp.tasks.vision.ImageSegmenter
ImageSegmenterOptions = mp.tasks.vision.ImageSegmenterOptions
VisionRunningMode = mp.tasks.vision.RunningMode

# Create a image segmenter instance with the live stream mode:
def print_result(result: List[Image], output_image: Image, timestamp_ms: int):
    print('segmented masks size: {}'.format(len(result)))

options = ImageSegmenterOptions(
    base_options=BaseOptions(model_asset_path='/path/to/model.task'),
    running_mode=VisionRunningMode.VIDEO,
    output_category_mask=True)
with ImageSegmenter.create_from_options(options) as segmenter:
    

Configuration options

This task has the following configuration options for Python applications:

Prepare data

Prepare your input as an image file or a numpy array, then convert it to a mediapipe.Image object. If your input is a video file or live stream from a webcam, you can use an external library such as OpenCV to load your input frames as numpy arrays.

# Load the input image from an image file.
mp_image = mp.Image.create_from_file('/path/to/image')

# Load the input image from a numpy array.
mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=numpy_image)
    

# Use OpenCV’s VideoCapture to load the input video.
# Load the frame rate of the video using OpenCV’s CV_CAP_PROP_FPS
# You need the frame rate to calculate the timestamp for each frame.
# Loop through each frame in the video using VideoCapture#read()

# Convert the frame received from OpenCV to a MediaPipe’s Image object.
mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=numpy_frame_from_opencv)
    

# Use OpenCV’s VideoCapture to start capturing from the webcam.
# Create a loop to read the latest frame from the camera using VideoCapture#read()

# Convert the frame received from OpenCV to a MediaPipe’s Image object.
mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=numpy_frame_from_opencv)
    

For a code example showing preparation of data for Image Segmenter, see the code example.

Run the task

The Image Segmenter uses the segment, segment_for_video and segment_async functions to trigger inferences. For image segmentation, this involves preprocessing input data, running segmentation model and postprocessing the raw model outputs to the segmented masks.

The following code examples show how to execute processing with the task model.

# Perform image segmentation on the provided single image.
# The image segmenter must be created with the image mode.
segmented_masks = segmenter.segment(mp_image)
    

# Perform image segmentation on the provided single image.
# The image segmenter must be created with the video mode.
segmented_masks = segmenter.segment_for_video(mp_image, frame_timestamp_ms)
    

# Send live image data to perform image segmentation.
# The results are accessible via the `result_callback` provided in
# the `ImageSegmenterOptions` object.
# The image segmenter must be created with the live stream mode.
segmenter.segment_async(mp_image, frame_timestamp_ms)
    

Note the following:

• When running in the video mode or the live stream mode, you must also provide the Image Segmenter task the timestamp of the input frame.
• When running in the image or the video model, the Image Segmenter task will block the current thread until it finishes processing the input image or frame.

For a more complete example of running Image Segmenter inferences, see the code example.

Handle and display results

The Image Segmenter outputs a list of Image data. If output_type is CATEGORY_MASK, the output is a list containing single segmented mask as an uint8 image. The pixel indicates the recognized category index of the input image. If output_type is CONFIDENCE_MASK, the output is a vector with size of category number. Each segmented mask is a float image within the range [0,1], representing the confidence score of the pixel belonging to the category.

The following sections show examples of the output data from this task:

Category confidence

The following images show a visualization of the task output for a category confidence mask. The confidence mask output contains float values between [0, 1].

Original image and category confidence mask output. Source image from the Pascal VOC 2012 dataset.

Category value

The following images show a visualization of the task output for a category value mask. The category mask range is [0, 255] and each pixel value represents the winning category index of the model output. The winning category index is has the highest score among the categories the model can recognize.

Original image and category mask output. Source image from the Pascal VOC 2012 dataset.