Abben
May 20, 2020
Edited: May 20, 2020

PixelLib：5行代码简单实现图像分割

Computer vision is evolving on a daily basis. Popular computer vision techniques such as image classification and object detection have been used extensively to solve a lot of computer vision problems. In image classification, an entire image is classified. Object detection extends image classification by detecting the location of individual objects present in an image.

Semantic and instance segmentation is possible with five lines of code.

Install PixelLib and its dependencies:

Install the latest version tensorflow(tensorflow 2.0) with:

  • pip3 install tensorflow

Install opencv-python with:

  • pip3 install opencv-python

Install scikit-image with:

  • pip3 install scikit-image

Install Pillow with:

  • pip3 install pillow

Install Pixellib:

  • pip3 install pixellib


import pixellib
from pixellib.semantic import semantic_segmentation

segment_image = semantic_segmentation()
segment_image.load_pascalvoc_model("deeplabv3_xception_tf_dim_ordering_tf_kernels.h5") 
segment_image.segmentAsPascalvoc("path_to_image", output_image_name = "path_to_output_image")


链接地址：https://medium.com/@olafenwaayoola/image-segmentation-with-six-lines-0f-code-acb870a462e8

0 comments