{"id":19315364,"url":"https://github.com/and2797/optical_character_recognition-","last_synced_at":"2026-05-16T09:03:01.075Z","repository":{"id":176196527,"uuid":"226259627","full_name":"AND2797/Optical_Character_Recognition-","owner":"AND2797","description":"Optical Character Recognition","archived":false,"fork":false,"pushed_at":"2020-08-02T17:40:58.000Z","size":313,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-06T03:41:52.289Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/AND2797.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":"2019-12-06T06:17:50.000Z","updated_at":"2020-08-02T17:41:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"e4c26b95-8adb-4ce5-b018-dac097d85c4c","html_url":"https://github.com/AND2797/Optical_Character_Recognition-","commit_stats":null,"previous_names":["and2797/optical_character_recognition-"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AND2797%2FOptical_Character_Recognition-","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AND2797%2FOptical_Character_Recognition-/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AND2797%2FOptical_Character_Recognition-/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AND2797%2FOptical_Character_Recognition-/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AND2797","download_url":"https://codeload.github.com/AND2797/Optical_Character_Recognition-/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240416992,"owners_count":19797920,"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":[],"created_at":"2024-11-10T01:06:26.295Z","updated_at":"2026-05-16T09:03:01.004Z","avatar_url":"https://github.com/AND2797.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Optical Character Recognition\nExtract text from images and classify accordingly. \n\n### Assumptions\n* Letters are reasonably spaced. \n* Letters should reasonably resemble the training data set. \n* Image should be naturally decipherable i.e free from any occlusions and obfuscations.\n\n### Output \n![Output](https://raw.githubusercontent.com/AND2797/Optical_Character_Recognition-/master/Output.png)\n### Observations\n* Common Confusions -\n  * True Label 'C' -\u003e Predicted Label 'G'\n  * True Label '1' -\u003e Predicted Label - '|' (I)\n  * True Label '4' -\u003e Predicted Label - 'A'\n  * True Label 'O'/ '0' -\u003e Predicted Label - 'O'/'0'/'Q'\n  * True Label '8' -\u003e Predicted Label 'B'\n  * True Label '6' -\u003e Predicted Label 'G'\n  * True Label '9' -\u003e Predicted Label 'g' (single storey) \n  \n  * Most of the confusions share highly similar features and construction, for example 4 and A, 8 and B, even C and G to some extent. \n### Tasks\n- [X] Train (EMNIST - Balanced)\n- [X] Extract text from images\n- [X] Pre-process to match EMNIST \n- [X] Test on extracted\n- [X] Improve accuracy and pre-processing\n- [ ] Realtime OCR from Video\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fand2797%2Foptical_character_recognition-","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fand2797%2Foptical_character_recognition-","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fand2797%2Foptical_character_recognition-/lists"}