{"id":16857662,"url":"https://github.com/brawer/cadasym","last_synced_at":"2025-03-18T12:14:53.419Z","repository":{"id":230062645,"uuid":"777864722","full_name":"brawer/cadasym","owner":"brawer","description":"Image corpus for Computer Vision on symbols in Swiss cadastral maps","archived":false,"fork":false,"pushed_at":"2024-07-24T15:36:06.000Z","size":720,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-01-24T18:12:09.167Z","etag":null,"topics":["cadastral","cadastre","computer-vision","corpus"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brawer.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":"2024-03-26T16:39:14.000Z","updated_at":"2024-07-24T15:36:09.000Z","dependencies_parsed_at":"2024-10-13T14:23:40.170Z","dependency_job_id":null,"html_url":"https://github.com/brawer/cadasym","commit_stats":null,"previous_names":["brawer/cadasym"],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brawer%2Fcadasym","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brawer%2Fcadasym/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brawer%2Fcadasym/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brawer%2Fcadasym/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brawer","download_url":"https://codeload.github.com/brawer/cadasym/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244217948,"owners_count":20417677,"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":["cadastral","cadastre","computer-vision","corpus"],"created_at":"2024-10-13T14:08:59.558Z","updated_at":"2025-03-18T12:14:53.395Z","avatar_url":"https://github.com/brawer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cadasym\n\nCadasym is a corpus for Computer Vision on symbols in cadastral maps.\n\n**Background:** Whenever a Swiss parcel or building changes its\ngeometry, land surveyors are required to submit a so-called “mutation\nplan” to the local authorities.  Today, this is done in a completely\ndigital workflow, but for most of the 20th century, plans were\nsubmitted on paper. By analyzing the archived plans, we would like to\neventually reconstruct the history how buildings have developed over\ntime. At the moment, the images in the corpus were all taken from\ncadastral mutation plans supplied by the [City of\nZürich](https://www.stadt-zuerich.ch/ted/de/index/geoz.html). In other\nSwiss municipalities, the plans should look identical, but they will\nlikely not have used the same equipment for scanning paper plans to\nelectronic images.\n\n**Purpose:** The images from this corpus are useful for testing,\nevaluating and training computer vision systems. The symbol\nrecognition task appears ideal for training Convolutional Neural\nNetworks with synthetic training data; or maybe it’s enough to go with\n“old-school” algorithmic computer vision.  Whatever solution we end up\nusing, we’ll need to evaluate its quality.\n\n**Corpus building:** To build the corpus, we wrote an ad-hoc [desktop\napplication](./corpus_builder) that extracts image snippet from\nscanned plans. Human users manually classified the image snippets into\none of the categories shown below.\n\n**Data download:** To download the corpus data, see the ZIP file\nin [Releases](https://github.com/brawer/cadasym/releases/).\n\n\n## Structure\n\nThe [released ZIP file](https://github.com/brawer/cadasym/releases/) contains\nPNG images, 256×256 pixel in size, where the symbol in question\nis located at the exact **center of the image.** Quite often, there are\nother symbols drawn nearby, or there is an overlapping line. That complication\nis what makes this an interesting problem. The PNG files are currently in one of these\nfolders:\n\n| Category              | Sample                                                                                                              |\n| --------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `white_circle`        | [\u003cimg src=\"./doc/samples/white_circle.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/white_circle.png)               |\n| `double_white_circle` | [\u003cimg src=\"./doc/samples/double_white_circle.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/double_white_circle.png) |\n| `black_dot`           | [\u003cimg src=\"./doc/samples/black_dot.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/black_dot.png)                     |\n| `double_black_circle` | [\u003cimg src=\"./doc/samples/double_black_circle.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/double_black_circle.png) |\n| `small_cross`         | [\u003cimg src=\"./doc/samples/small_cross.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/small_cross.png)                 |\n| `large_cross`         | [\u003cimg src=\"./doc/samples/large_cross.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/large_cross.png)                 |\n| `triangle`            | [\u003cimg src=\"./doc/samples/triangle.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/triangle.png)                 |\n| `other`               | [\u003cimg src=\"./doc/samples/other.png\" width=\"64\" height=\"64\" /\u003e](./doc/samples/other.png)                             |\n\nNote: We’ll likely split the `white_circle` category into several categories by circle size. Because this is rather trivial for a computer (we can just measure\nthe circle radius), we’ll do this later. Also, we’ll likely add more categories over time.\n\n\n## License\n\n[Public Domain (CC0-1.0)](https://creativecommons.org/publicdomain/zero/1.0/): To the\nextent possible under law, we have waived all copyright and related or\nneighboring rights to this work. This work is published from Switzerland.\n\n![Public Domain](https://mirrors.creativecommons.org/presskit/buttons/88x31/svg/cc-zero.svg)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrawer%2Fcadasym","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrawer%2Fcadasym","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrawer%2Fcadasym/lists"}