{"id":16282877,"url":"https://github.com/dito97/neural-binarization","last_synced_at":"2025-04-08T18:22:39.898Z","repository":{"id":218820328,"uuid":"626556990","full_name":"DiTo97/neural-binarization","owner":"DiTo97","description":"toolkit for efficient semantic document image binarization (DIB)","archived":false,"fork":false,"pushed_at":"2024-07-16T08:01:07.000Z","size":1869,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-03T12:56:50.030Z","etag":null,"topics":["document-image-binarization","image-segmentation","transformers"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DiTo97.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-04-11T17:52:08.000Z","updated_at":"2024-08-25T01:01:43.000Z","dependencies_parsed_at":"2024-01-24T01:28:50.021Z","dependency_job_id":"1e662382-4e13-4c4d-87c2-d726604031db","html_url":"https://github.com/DiTo97/neural-binarization","commit_stats":null,"previous_names":["dito97/neural-binarization"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiTo97%2Fneural-binarization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiTo97%2Fneural-binarization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiTo97%2Fneural-binarization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiTo97%2Fneural-binarization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DiTo97","download_url":"https://codeload.github.com/DiTo97/neural-binarization/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247898911,"owners_count":21014801,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["document-image-binarization","image-segmentation","transformers"],"created_at":"2024-10-10T19:11:54.978Z","updated_at":"2025-04-08T18:22:39.874Z","avatar_url":"https://github.com/DiTo97.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Binarization Segformer\n\nA semantic segmentation model for pixel-wise document image binarization.\n\n## TODOs\n\n- [ ] fine-tune Segformer on 1024 $\\times$ 1024 images;\n- [ ] set [`reduce_labels=True`](https://huggingface.co/docs/transformers/main/model_doc/segformer#transformers.SegformerImageProcessor.do_reduce_labels) in Segformer processor to ignore the background;\n- [ ] compare valid DIBCO metrics with SauvolaNet's [paper](https://arxiv.org/pdf/2105.05521.pdf).\n\n## Overview\n\nSegformer is an efficient semantic segmentation model introduced by [Xie et al.](https://arxiv.org/abs/2105.15203) in 2021.\n\nIn this repository, we will provide a fine-tuning of Segformer for pixel-wise document image binarization.\n\n## Dataset\n\nThe dataset is an ensemble of 14 datasets replicating the setting used in SauvolaNet by [Li et al.](https://arxiv.org/abs/2105.05521) in 2021.\n\n\u003cimg src=\"images/example.png\" width=\"75%\" /\u003e\n\n\u003e Figure 1. An example pair from the Bickley diary dataset\n\nFor more information on the dataset, see SauvolaNet's official [repository](https://github.com/Leedeng/SauvolaNet).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdito97%2Fneural-binarization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdito97%2Fneural-binarization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdito97%2Fneural-binarization/lists"}