dhlab-epfl / Dhsegment
Licence: gpl-3.0
Generic framework for historical document processing
Stars: ✭ 282
Programming Languages
Labels
Projects that are alternatives of or similar to Dhsegment
automated-deep-photo-style-transfer
TensorFlow implementation for the paper "Automated Deep Photo Style Transfer"
Stars: ✭ 92 (-67.38%)
Mutual labels: segmentation
Sipmask
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
Stars: ✭ 255 (-9.57%)
Mutual labels: segmentation
Wshp
Code for CVPR'18 spotlight "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer"
Stars: ✭ 273 (-3.19%)
Mutual labels: segmentation
LSDNN
A robust laser stripe extraction method for structured-light vision sensing
Stars: ✭ 17 (-93.97%)
Mutual labels: segmentation
GuidedLabelling
Exploiting Saliency for Object Segmentation from Image Level Labels, CVPR'17
Stars: ✭ 35 (-87.59%)
Mutual labels: segmentation
Detectron.pytorch
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
Stars: ✭ 2,805 (+894.68%)
Mutual labels: segmentation
cellcount
A Convolutional Neural Network for Segmenting and Counting Cells in Microscopy Images
Stars: ✭ 51 (-81.91%)
Mutual labels: segmentation
Glnet
[CVPR 2019, Oral] "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images" by Wuyang Chen*, Ziyu Jiang*, Zhangyang Wang, Kexin Cui, and Xiaoning Qian
Stars: ✭ 254 (-9.93%)
Mutual labels: segmentation
Slicer
Multi-platform, free open source software for visualization and image computing.
Stars: ✭ 263 (-6.74%)
Mutual labels: segmentation
PyTorch-UNet
PyTorch Implementation for Segmentation and Saliency Prediction
Stars: ✭ 21 (-92.55%)
Mutual labels: segmentation
Mask-Propagation
[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code 🌟. Semi-supervised video object segmentation evaluation.
Stars: ✭ 71 (-74.82%)
Mutual labels: segmentation
Cosnet
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR19)
Stars: ✭ 270 (-4.26%)
Mutual labels: segmentation
ArabicProcessingCog
A Python package that do stemming, tokenization, sentence breaking, segmentation, normalization, POS tagging for Arabic language.
Stars: ✭ 19 (-93.26%)
Mutual labels: segmentation
Charlescd
CharlesCD is an open source tool that makes deployments more agile, continuous and safe, which allows development teams to perform hypothesis validations with a specific group of users, simultaneously.
Stars: ✭ 275 (-2.48%)
Mutual labels: segmentation
dilation-keras
Multi-Scale Context Aggregation by Dilated Convolutions in Keras.
Stars: ✭ 72 (-74.47%)
Mutual labels: segmentation
Jejunet
Real-Time Video Segmentation on Mobile Devices with DeepLab V3+, MobileNet V2. Worked on the project in 🏝 Jeju island
Stars: ✭ 258 (-8.51%)
Mutual labels: segmentation
Turbo Download Manager
a multi-browser download manager with multi-threading support
Stars: ✭ 282 (+0%)
Mutual labels: segmentation
Apc Vision Toolbox
MIT-Princeton Vision Toolbox for the Amazon Picking Challenge 2016 - RGB-D ConvNet-based object segmentation and 6D object pose estimation.
Stars: ✭ 277 (-1.77%)
Mutual labels: segmentation
Pytorch Saltnet
Kaggle | 9th place single model solution for TGS Salt Identification Challenge
Stars: ✭ 270 (-4.26%)
Mutual labels: segmentation
dhSegment
dhSegment is a tool for Historical Document Processing. Its generic approach allows to segment regions and extract content from different type of documents. See some examples here.
The complete description of the system can be found in the corresponding paper.
It was created by Benoit Seguin and Sofia Ares Oliveira at DHLAB, EPFL.
Installation and usage
The installation procedure and examples of usage can be found in the documentation (see section below).
Demo
Have a try at the demo to train (optional) and apply dhSegment in page extraction using the demo.py script.
Documentation
The documentation is available on readthedocs.
If you are using this code for your research, you can cite the corresponding paper as :
@inproceedings{oliveiraseguinkaplan2018dhsegment,
title={dhSegment: A generic deep-learning approach for document segmentation},
author={Ares Oliveira, Sofia and Seguin, Benoit and Kaplan, Frederic},
booktitle={Frontiers in Handwriting Recognition (ICFHR), 2018 16th International Conference on},
pages={7--12},
year={2018},
organization={IEEE}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].