{"id":16359322,"url":"https://github.com/gaborvecsei/ocr-libraries","last_synced_at":"2026-01-30T14:21:05.012Z","repository":{"id":84266156,"uuid":"68384402","full_name":"gaborvecsei/OCR-libraries","owner":"gaborvecsei","description":"Google Cloud Vision, Tesseract and Asprise OCR ibrary tests","archived":false,"fork":false,"pushed_at":"2016-10-07T17:30:35.000Z","size":18314,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-06-05T05:46:49.698Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gaborvecsei.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":"2016-09-16T13:59:10.000Z","updated_at":"2019-09-17T05:51:56.000Z","dependencies_parsed_at":"2023-05-24T04:45:27.262Z","dependency_job_id":null,"html_url":"https://github.com/gaborvecsei/OCR-libraries","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gaborvecsei/OCR-libraries","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FOCR-libraries","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FOCR-libraries/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FOCR-libraries/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FOCR-libraries/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gaborvecsei","download_url":"https://codeload.github.com/gaborvecsei/OCR-libraries/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaborvecsei%2FOCR-libraries/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28914058,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-30T12:13:43.263Z","status":"ssl_error","status_checked_at":"2026-01-30T12:13:22.389Z","response_time":66,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":[],"created_at":"2024-10-11T02:08:05.423Z","updated_at":"2026-01-30T14:21:04.985Z","avatar_url":"https://github.com/gaborvecsei.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# OCR Library Comparison\n\nSo I wanted to compare popular OCR libraries so we can see the pros and cons.\n\n## Update:\n\nI wrote a post about this topic at [my blog](https://gaborvecsei.wordpress.com/)\n\n**This work and the blog post was mentioned at [Rsipvision's Computer Vision News](http://www.rsipvision.com/ComputerVisionNews-2016October/#24)**\n\n## Results:\n\nI tested with hungarian language because that's more complex than the english.\n\n[This is the *.pdf* I used for testing](https://github.com/gaborvecsei/OCR-libraries/blob/master/szamla.pdf)\n\n[And this is the *.png* image I generated from that image](https://github.com/gaborvecsei/OCR-libraries/blob/master/szamla.png)\n\n### Tesseract with image\n\n, . . Szamla/Invozce (Minta, ) Az eredeti bizonylat másolata, csak tájékoztatásra! Sorszám/lnvoice No. 287/2008/V Szállító/ Sold by Vev /Client Minta Kft Némedi László 1022 Budapest Budapest Törökvész u. 30/a Szent I. u. 34. 1200 Fizetési mód/ Teljesítés id pontja/ Számla kelte/ Esedékesseg/ Method of payment Date of fulfilment Date of invoice Due Készpénz/ Cash 2008. 10. 17. 2008. 10. 17. 2008. 10. 17. Megnevezés/ VTSZ/ SZJ/ Mennyiség/ Mee/ Egységár/ Nettó/ Áfa %/ Áfaérték/ Bruttó/ Description VTSZ/ SZJ Nr. Amount Unit Unit price Net VAT % Am. of VAT Gross Minta termék 10db 50 EUR 500 EUR 20% 100 EUR 600 EUR 20% 500 EUR 100 EUR 26 200 Ft 600 EUR Összesen/ Total 500 EUR 100 EUR 26 200 Ft 600 EUR Fizetend végösszeg/ Total: 600 EUR azaz Hatszáz Euró. (Árfolyam/Exchange rate: 262,0000 Ft/EUR) Köszönjük a vásárlást! Ez a számla a Kulcs-Solt Számítástechnika Zrt. rendszerével készült http://www.kulcs-solt.hu This invoice was prepared using the program ol Key-Solt Software Co. http://www.kulcs-solt.hu A számla a 47/2007. (Xll.29.) PM rendeletnek megfelel. The invoice is in compliance with the PM Decree 47/2007. (Xll.29.).\n\n### Tesseract with pdf\n\nl . . Szamla/Invozce ( Minta ) Az eredeti bizonylat másolata, csak tájékoztatásra! Sorszám/lnvoice No. 287/2008/V Szállító/ Solcl by Vevő/ Client Minta Kft Némedi László 1022 Budapest Budapest Törökvész u. 30/a Szent I. u. 34. 1200 Fizetési mód/ Telj esítés időpontja/ Számla kelte/ Esedékesség/ Method of payment Date of fulfilment Date of invoice Due Készpénz/ Cash 2008. 10. 17. 2008. 10. 17. 2008. 10. 17. Megnevezés/ VTSZ/ SZJ/ Mennyiség/ Mee/ Egységár/ Nettó/ Áfa %/ Áfaérték/ Bruttó/ Description VTSZ/ SZJ Nr. Amount Unit Unit price Net VAT % Am. of VAT Gross Minta termék 10db 50 EUR 500 EUR 20% 100 EUR 600 EUR Áfa % / VAT % Nettó/ Net ÁFA/ VAT ÁFA/ VAT (Ft) Bruttó/ Gross 20% 500 EUR 100 EUR 26 200 Ft 600 EUR Összesen/ Total 500 EUR 100 EUR 26 200 Ft 600 EUR Fizetendő végösszeg/ Total: 600 EUR azaz Hatszáz Euró. (Árfolyam/Exchange rate: 262,0000 Ft/EUR) Köszönjük a vásárlást! Ez a számla a Kulcs-Soft Számítástechnika Zrt. rendszerével készült http://www.kulcs-soit.hu This invoice was prepared using the program of Key-Soft Software Co. http://www.kulcs-soit.hu A számla a 47/2007. (Xll.29.) PM rendeletnek megfelel. The invoice is in compliance with the PM Decree 47/2007. (Xll.29.).\n\n### Asprise with image\n\nSzdmla/Invoice (Minta) Az eredeti bizonylat mésolata, csak téjékoztatésra! Sorszém/Invoice No. V Szélll’té/ Sold by Minta Kft 1022 Budapest T6r6kvész u. 30/a Vev / Client Ne'medi Ldszlo' Budapest Szent I. u. 34. 1200 ' Fizetési méd/ Teljesités id pontja/ Szamla kelte/ Esedékesség/ ‘ Method of payment Date of fulfilment Date of invoice Due Készpénz/ Cash 2008. 10. 17. 2008. 10. 17. 2008. 10. 17. 'Megnevezés/ VTSZ/ SZJ/ Mennyiség/ Mee/ Egységér/ Netté/ Afa %/ Afaérték/ Brutté/ ‘ Description VTSZ/ SZJ Nr. Amount Unit Unit price Net VAT % Am. of VAT Gross 50 EUR 500 EUR 20% 100 EUR 600 EUR Minta termék 10 db Afa % / VAT % Netté/ Net AFA/ VAT AFA/ VAT (Ft) Brutté/ Gross 20% 500 EUR 100 EUR 26 200 Ft 600 EUR ésszesen/ Total 500 EUR 100 EUR 26 200 Ft 600 EUR Fizetend végésszeg/ Total: 600 EUR azaz Hatszaz Euro. (Arfolyam/Exchange rate: 262.0000 Ft/EUR) KoszonjiJk a vésérlést! Ez a szamla a Kulcs-Soft Szamitastechnika Zrt. rendszerével késziilt http://www.ku|cs-soft.hu This invoice was prepared using the program of Key-Soft Software Co. http://www.ku|cs-soft.hu A szamla a 47/2007. (X||.29.) PM rendeletnek megfelel. The invoice is in compliance with the PM Decree 47/2007. (X||.29.). Afa % / VAT % Netté/ Net AFA/ VAT AFA/ VAT (Ft) Brutté/ Gross\n\n### Asprise with pdf\n\nMinta Kft Ne'medi Ldszlo' 1022 Budapest Budapest T6r6kvész u. 30/a Szent I. u. 34. 1200 KészénjUk a vésérlést!\n\n### Google (only image)\n\n*(Google cloud vision can't process pdf files so I could only test it on the .png file)*\n\nSzamla/Invoice (Minta) Az eredeti bizonylat masolata, csak tajékoztatasra! Sorszam/Invoice No. 287/2008 V Szallitol Sold by Vev Client Minta Kft 1022 Budapest Némedi Laszlo Budapest Torok vész u. 30/a Szent I. u. 34 1200 Fizetési mod Teljesités id pontja/ Szamla kelte/ Esedékesség/ Method of payment Date of men Date of invoice Due 2008. 10. 17. Készpénz/ Cash 2008. 10. 17 2008. 1 Egységar/ Megnevezés/ VTSZI SZJ Mennyiség Mee/ Netto/ Afa Afaérték Brutto Description VTSZI SZJ Nr. Net VAT Am. of VAT Gross Amount Unit Unit price Minta termék 50 EUR 500 EUR 20% 0 db 00 EUR 600 EUR AFA/ VAT (Ft) Afa VAT Netto/ Net AFA VAT Brutto/ Gross 500 EUR 100 EUR 600 EUR 20% 26 200 Ft 600 EUR Osszesen Tota 500 EUR 26 200 Ft 100 EUR Fizetend végosszeg/ Total: 600 EUR azaz Hatszaz Euro Arfolyam/ Exchange rate 262,0000 Ft/EUR) Ez a szamla a Kulcs-Soft Sza astechnika Zrt. rendszerével kés http This invoice was prepared using the progra of Key-Soft Software Co. http://www.kulcs-soft.hu A szamla a 47/2007. (XII.29.) PM rendeletnek megfele The invoice is in compliance with the PM Decree 47/2007. (XII.29\n\n## Thoughts\n\nAs you can see, Tesseract and Google is better than Asprise but unfortunately with Google we can't use pdfs.\n\nBtw...That was an easy problem because we can say that this was a scanned document. If the image is a little bit rotated than the only solution is Google or you can rotate back and things like that with image processing. And after that tesseract is cool too.\n\n## Google Cloud Vision Tutorial\n\nWhen I wanted to use Google Cloud vision for the first time I couldn't start fast because theres were no easy tutorials on the net. So you can see my code and I think you will be able to understand it better.\n\n[*You can find the code here*](https://github.com/gaborvecsei/OCR-libraries/blob/master/src/GoogleDetection.java)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaborvecsei%2Focr-libraries","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgaborvecsei%2Focr-libraries","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaborvecsei%2Focr-libraries/lists"}