Skip to content
A Simple Deep Learning Based Image Segmentation Tool
MATLAB Python
Branch: master
Clone or download
Latest commit 27b1bcf May 24, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Image1.jpg Add files via upload May 17, 2019
LICENSE Initial commit May 17, 2019
README.md Update README.md May 24, 2019
User Manual.pdf Add files via upload May 17, 2019
autoArrangeFigures.m Add files via upload May 17, 2019
deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz Add files via upload May 17, 2019
sampleResult.jpg Add files via upload May 17, 2019
segment_image.m Add files via upload May 17, 2019
segmenter.py Add files via upload May 17, 2019

README.md

A Simple Deep Learning Based Image Segmentation Tool

This is a simple tool that can be used for scemantic segmentations of coloured images. This tool adopts a pretrained deep learning model for segmentation. It needs both Python and Matlab installations. Also, some additional Python libraries are necessary.

This tool uses a model which is based on MobileNetV2 [1] architecture and is pretrained with Microsoft COCO dataset [2]. The model can segment and identify the objects: aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, dining table, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, and tv.

Segmentation Sample

Getting Started

Download the branch from Github. After that, please read and follow the instructions in User Manual.pdf file.

References

  1. MobileNetV2
  2. Microsoft COCO dataset
You can’t perform that action at this time.