{"id":16356076,"url":"https://github.com/joehowarth/goscanner","last_synced_at":"2025-07-22T19:33:38.797Z","repository":{"id":100830095,"uuid":"106126339","full_name":"JoeHowarth/GoScanner","owner":"JoeHowarth","description":"Converts images of Go boards to .sgf file using OpenCV and Keras","archived":false,"fork":false,"pushed_at":"2018-05-12T17:25:14.000Z","size":42930,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-04-07T14:23:48.296Z","etag":null,"topics":["computer-vision","deep-learning","opencv","python","sgf-files"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JoeHowarth.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2017-10-07T19:55:00.000Z","updated_at":"2025-03-07T02:52:00.000Z","dependencies_parsed_at":"2023-06-25T23:01:07.413Z","dependency_job_id":null,"html_url":"https://github.com/JoeHowarth/GoScanner","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/JoeHowarth/GoScanner","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoeHowarth%2FGoScanner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoeHowarth%2FGoScanner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoeHowarth%2FGoScanner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoeHowarth%2FGoScanner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JoeHowarth","download_url":"https://codeload.github.com/JoeHowarth/GoScanner/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JoeHowarth%2FGoScanner/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266561321,"owners_count":23948625,"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","status":"online","status_checked_at":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["computer-vision","deep-learning","opencv","python","sgf-files"],"created_at":"2024-10-11T01:42:37.703Z","updated_at":"2025-07-22T19:33:38.789Z","avatar_url":"https://github.com/JoeHowarth.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GoScanner\n### Currently Non-Working (Planning to fix at some point!)\n\n## Purpose:\nWhen playing Go on a physical board, it can be a pain to record the game to learn from later. \nParticularly, the .sgf tree format provides an easy way to view, send and make hypothetical changes to a \ncompleted game. This project converts webcam pictures of a game into a digital reprentation of each turn, \nthen convertes those states into a .sgf file.\n\n\n## Technical Summary:\nThis project takes an image of a Go board as input and outputs a matrix representation of the game's state.\n\n\nThe edges of the Go board are detected in the inputted image, which is then transformed to a square, top-down perspective.\nThe image is then segmented by each square, then fed into a Convolutional Neural Network (CNN) trained to classify each \nsub-image as containing a white piece, black piece or no piece. The classification for each position is stored in an array, \nand the array representation is converted to a .sgf representation. This is then written and can be viewed by most types of Go \nsoftware.\n\n## Planned additions\nTaking multiple game states and ordering them into a tree structure.\n\nCleaning up the pipeline into a user-friendly api that can be accessed by a frontend \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjoehowarth%2Fgoscanner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjoehowarth%2Fgoscanner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjoehowarth%2Fgoscanner/lists"}