{"id":20514337,"url":"https://github.com/devashishprasad/embossed-text-reader","last_synced_at":"2025-04-14T00:13:08.850Z","repository":{"id":52179070,"uuid":"138977864","full_name":"DevashishPrasad/Embossed-Text-Reader","owner":"DevashishPrasad","description":"This is a tesseract based OCR to read Embossed text on metals. It can also be use as a general OCR.","archived":false,"fork":false,"pushed_at":"2021-05-06T04:27:54.000Z","size":22182,"stargazers_count":31,"open_issues_count":3,"forks_count":12,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-14T00:12:58.031Z","etag":null,"topics":["ocr","opencv-python","opencv3","python","python3"],"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/DevashishPrasad.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}},"created_at":"2018-06-28T06:48:00.000Z","updated_at":"2025-01-14T09:06:07.000Z","dependencies_parsed_at":"2022-08-24T04:01:18.721Z","dependency_job_id":null,"html_url":"https://github.com/DevashishPrasad/Embossed-Text-Reader","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FEmbossed-Text-Reader","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FEmbossed-Text-Reader/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FEmbossed-Text-Reader/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FEmbossed-Text-Reader/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DevashishPrasad","download_url":"https://codeload.github.com/DevashishPrasad/Embossed-Text-Reader/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248799956,"owners_count":21163404,"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":["ocr","opencv-python","opencv3","python","python3"],"created_at":"2024-11-15T21:15:58.282Z","updated_at":"2025-04-14T00:13:08.809Z","avatar_url":"https://github.com/DevashishPrasad.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Embossed-Text-Reader\nThis is a tesseract based OCR to read Embossed text on metals. It can also be use as a general OCR.\n\nThis is not generalized solution. The satements and parameters of some funtions will changed according to the texture,\ncolor, lighting effect and visibility of text of image.\n\nTesseract is an open-sourced OCR which is capable of reading text from papers, pdfs and other clean formats. Tesseract fails when \ntried to perform OCR on noisy and dirty images (for eg. Embossed or Engraved text). The code uses opencv image filtering techniques\nto filter the images as clean as possible and then feeds it to Tesseract.  \n\n## Dependencies\n  Python\u003cbr\u003e \n  OpenCV\u003cbr\u003e\n  Tesseract\u003cbr\u003e\n  Numpy\u003cbr\u003e\n  imutils\u003cbr\u003e\n\n### There are three files - \n  1. picture_from_webcam.py clicks a single picture from webcam and performs OCR on it\n  2. read_from_disk.py loads a picture from an image file\n  3. video_from_webcam.py feeds the realtime video from the webcam (doesn't perform as expected)\n\n## Example\n#### Edged image (canny) with dialation\n\u003cimg src=\"images/ger3.png\" alt=\"Picture not availble in your browser\"/\u003e\n\n#### Finding and deleting unessesary contours\n\n\u003cimg src=\"images/ger4.png\" alt=\"Picture not availble in your browser\"/\u003e\n\n#### Inverted threshold image\n\n\u003cimg src=\"images/ger2.png\" alt=\"Picture not availble in your browser\"/\u003e\n\n#### Results \n\n\u003cimg src=\"images/ger1.png\" alt=\"Picture not availble in your browser\"/\u003e\n\n## Sample results - \n\u003cimg src=\"images/pro1.png\" alt=\"Picture not availble in your browser\"/\u003e\n\u003cimg src=\"images/pro2.png\" alt=\"Picture not availble in your browser\"/\u003e\n\u003cimg src=\"images/pro3.png\" alt=\"Picture not availble in your browser\"/\u003e\n\u003cimg src=\"images/2018.png\" alt=\"Picture not availble in your browser\"/\u003e\n\n\nThe code may fail sometimes but tuning parameters of canny and appropriate dialation will improve results\n\n### Data.zip contains all data I have used during implementation of this project\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevashishprasad%2Fembossed-text-reader","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevashishprasad%2Fembossed-text-reader","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevashishprasad%2Fembossed-text-reader/lists"}