简体中文 | English
 |
 |
 |
 |
| Generic segmentation | Human segmentation | RS building segmentation | Medical segmentation |
 |
 |
 |
|
| Industrial quality inspection | Generic video segmentation | 3D medical segmentation | |
- [2022-12-16] 🔥 EISeg 1.1 has been released!
- Added the annotation ability for detection , which can be marked manually or using the detection model PicoDet-S for labeling.
- Detection annotation result supports various formats such as COCO, VOC and YOLO.
- Added LabelMe JSON format for segmentation result.
- [2022-09-16] 🔥 The annotation model MUSCLE has been accepted by MICCAI 2022. For details, please refer to MUSCLE, the model can be downloaded here.
EISeg (Efficient Interactive Segmentation) is an efficient and intelligent interactive segmentation annotation software developed based on PaddlePaddle. It covers a large number of high-quality segmentation models in different directions such as generic scenarios, portrait, remote sensing, medical treatment, video, etc., providing convenience to the rapid annotation of semantic and instance labels with reduced cost. In addition, by applying the annotations obtained by EISeg to other segmentation models provided by PaddleSeg for training, high-performance models with customized scenarios can be created, integrating the whole process of segmentation tasks from data annotation to model training and inference.
- If you have any problem or suggestion on EISeg, please send us issues through GitHub Issues.
- Welcome to Join EISeg WeChat Group
- Installation
- Image Segmentation Annotation
- Video Segmentation Annotation
- Remote Sensing Segmentation
- Medical Treatment
- Detection
- Tool script
- 2022.12.16 1.1.0： 【1】 Added the annotation ability for detection , which can be marked manually or using the detection model PicoDet-S for labeling. 【2】Detection annotation result supports various formats such as COCO, VOC and YOLO. 【3】Added LabelMe JSON format for segmentation result.
- 2022.07.20 1.0.0：【1】Add the ability of interactive video object segmentation. 【2】Add 3D annotation model for abdominal multi-organ【3】Added 3D annotation model for CT vertebra.
- 2022.04.10 0.5.0: 【1】Add chest_xray interactive model;【2】Add MRSpineSeg interactive model;【3】Add industrial quality inspection model;【4】Fix geo-transform / CRS error when shapefile saved.
- 2021.12.14 0.4.1: 【1】Fix the bug of crashing; 【2】Newly add the post-labeling operation of remote sensing building images.
- 2021.11.16 0.4.0: 【1】 Convert dynamic graph inference into static graph inference with ten times' increase in the speed of single click; 【2】 Add the function of remote sensing image labeling, support the selection of multi-spectral data channels; 【3】 Support the processing of slicing (multi squre division) of large size data; 【4】 Add medical image labeling function, support the reading dicom format and the selection of window width and position.
- 2021.09.16 0.3.0：【1】Complete the function of polygon editing with support for editing the results of interactive annotation；【2】Support CH/EN interface；【3】Support saving as grayscale/pseudo-color labels and COCO format；【4】More flexible interface dragging；【5】Achieve the dragging of label bar, and the generated mask is overwritten from top to bottom.
- 2021.07.07 0.2.0: Newly added contrib：EISeg，which enables rapid interactive annotation of portrait and generic images.
- Our gratitude goes to Developers including Zhiliang Yu, Yizhou Chen, Lin Han, Jinrui Ding, Yiakwy, GT, Youssef Harby, Nick Nie and the support of RITM and MiVOS.
- Thanks for the labelling deisgn of LabelMe and LabelImg.
- Thanks for Weibin Liao to provide the pretrain model of ResNet50_DeeplabV3.
- Thanks for support of Junjie Guo and Jiajun Feng on MRSpineSeg model.
If you find our project useful in your research, please consider citing ：
@article{hao2022eiseg,
title={EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle},
author={Hao, Yuying and Liu, Yi and Chen, Yizhou and Han, Lin and Peng, Juncai and Tang, Shiyu and Chen, Guowei and Wu, Zewu and Chen, Zeyu and Lai, Baohua},
journal={arXiv e-prints},
pages={arXiv--2210},
year={2022}
}
@inproceedings{hao2021edgeflow,
title={Edgeflow: Achieving practical interactive segmentation with edge-guided flow},
author={Hao, Yuying and Liu, Yi and Wu, Zewu and Han, Lin and Chen, Yizhou and Chen, Guowei and Chu, Lutao and Tang, Shiyu and Yu, Zhiliang and Chen, Zeyu and others},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={1551--1560},
year={2021}
}