Tesseract (perangkat lunak): Perbedaan antara revisi
Konten dihapus Konten ditambahkan
k Bot: perubahan kosmetika |
perbaikan panggilan -- templat salah: "Cat main" -> "Main" | t=579 su=70 in=73 at=70 -- only 13 edits left of totally 84 possible edits | edr=000-0001(!!!) ovr=010-1111 aft=000-0001 |
||
| (12 revisi perantara oleh 7 pengguna tidak ditampilkan) | |||
Baris 1:
{{Dalam perbaikan}}
Dalam [[perangkat lunak komputer]], '''Tesseract''' adalah mesin [[pengenal karakter optik]] gratis. Tesseract pada awalnya dikembangkan sebagai perangkat lunak berpemilik di [[Hewlett-Packard]] antara tahun 1985 hingga 1995. Setelah sepuluh tahun tanpa perkembangan apapun yang terjadi, Hewlett Packard dan [[UNLV]] merilis Tesseract sebagai sumber terbuka di tahun 2005. Tesseract saat ini sedang dikembangkan oleh [[Google]] dan dirilis di bawah [[Lisensi Apache]], Version 2.0.▼
{{Infobox software
| name = Tesseract
| logo size = 250px
| screenshot = File:Tesseract v3.02.png
| screenshot size = 250px
| caption = Tesseract 3.02 running on Gnome Terminal 3.8.0. "input_image.tif" is the input document which will be rendered as "output_text.txt" by Tesseract.
| collapsible =
| author = Ray Smith, [[Hewlett-Packard]]<ref name="TesseractHomePage">{{cite web|url = https://github.com/tesseract-ocr/tesseract/|title = tesseract-ocr|accessdate = 2016-03-08|last = Google|authorlink = |year = 2008}}</ref>
| developer = [[Google]]
| released =
| latest release version = 4.1.1
| latest release date = {{Start date and age|2019|12|26}}<ref name="tesseract-releases">{{cite web|url=https://github.com/tesseract-ocr/tesseract/releases|title = Releases - tesseract-ocr/tesseract|accessdate = 5 January 2020|via=[[GitHub]]}}</ref>
| latest preview version =
| latest preview date =
| programming language = [[C (programming language)|C]] and [[C++]]
| operating system = [[Linux]], [[Microsoft Windows|Windows]], and [[macOS]] ([[x86]])
| platform =
| language = Interface: [[English language|English]] <br/> Recognition:
[[Afrikaans language|Afrikaans]], [[Albanian language|Albanian]], [[Arabic language|Arabic]], [[Azerbaijani language|Azerbaijani]], [[Basque language|Basque]], [[Belarusian language|Belarusian]], [[Bengali language|Bengali]], [[Bulgarian language|Bulgarian]], [[Catalan language|Catalan]], [[Czech language|Czech]], [[Cherokee language|Cherokee]], [[Croatian language|Croatian]], [[Danish language|Danish]], [[Dutch language|Dutch]], [[English language|English]], [[Esperanto language|Esperanto]], [[Estonian language|Estonian]], [[Finnish language|Finnish]], [[French language|French]], [[Galician language|Galician]], [[German language|German]], [[Greek language|Greek]], [[Hindi language|Hindi]], [[Hungarian language|Hungarian]], [[Indonesian language|Indonesian]], [[Italian language|Italian]], [[Japanese language|Japanese]], [[Kannada language|Kannada]], [[Korean language|Korean]], [[Latvian language|Latvian]], [[Lithuanian language|Lithuanian]], [[Malayalam language|Malayalam]], [[Macedonian language|Macedonian]], [[Maltese language|Maltese]], [[Malay language|Malay]], [[Norwegian language|Norwegian]], [[Polish language|Polish]], [[Portuguese language|Portuguese]], [[Romanian language|Romanian]], [[Russian language|Russian]], [[Serbian language|Serbian]], [[Slovak language|Slovak]], [[Slovenian language|Slovenian]], [[Spanish language|Spanish]], [[Swahili language|Swahili]], [[Swedish language|Swedish]], [[Tagalog language|Tagalog]], [[Tamil language|Tamil]], [[Telugu language|Telugu]], [[Thai language|Thai]], [[Turkish language|Turkish]], [[Ukrainian language|Ukrainian]] & [[Vietnamese language|Vietnamese]] (more can be added using included training files)
| genre = [[Optical character recognition]]
| license = [[Apache License 2.0]]
| repo = <!-- from wikidata -->
| website = <!-- from wikidata -->
}}
▲Dalam [[perangkat lunak komputer]], '''Tesseract''' adalah mesin [[Pengenalan karakter optis|pengenal karakter optik]] gratis. Tesseract pada awalnya dikembangkan sebagai perangkat lunak berpemilik di [[Hewlett-Packard]] antara tahun 1985 hingga 1995. Setelah sepuluh tahun tanpa perkembangan apapun yang terjadi, Hewlett Packard dan [[UNLV]] merilis Tesseract sebagai sumber terbuka
Tesseract dianggap salah satu perangkat lunak mesin OCR bebas yang paling akurat yang tersedia saat ini.<ref name="Linux.com"> {{cite web|url = http://www.linux.com/articles/57222|title = Google's Tesseract OCR engine is a quantum leap forward|accessdate = 2008-07-18|last = Willis |first = Nathan|authorlink = |year = 2006|month = September}}</ref>
Baris 12 ⟶ 38:
== Pranala luar ==
* [http://code.google.com/p/tesseract-ocr/ Tesseract OCR] Project page on Google Code
* [http://www.isri.unlv.edu/ Information Science Research Institute at the University of Nevada, Las Vegas] {{Webarchive|url=https://web.archive.org/web/20100314225206/http://www.isri.unlv.edu/ |date=2010-03-14 }} Information Science Research Institute at the University of Nevada, Las Vegas
* http://tesseract-ocr.repairfaq.org/ - C/C++ structure of Tesseract extracted from Doxyfied source code (based on Tesseract V1.03)
* [http://sourceforge.net/projects/archivista Archivista Box] - A complete GPL document management system based on Tesseract and Linux.
* [http://www.win.tue.nl/~aeb/linux/ocr/tesseract.html Tesseract - Summary] - some patches for training on a 64-bit machine.
* [http://tesseract-ocr.googlecode.com/files/TesseractOSCON.pdf Tesseract OCR Engine] {{Webarchive|url=https://web.archive.org/web/20100216031725/http://tesseract-ocr.googlecode.com/files/TesseractOSCON.pdf |date=2010-02-16 }} What it is, where it came from, where it is going.
* [http://vietocr.sf.net/ VietOCR] - Java/.NET GUI frontend for Tesseract OCR engine
Baris 23 ⟶ 49:
[[Kategori:Pengenal karakter optik]]
[[Kategori:Google]]
▲[[de:Tesseract (Software)]]
| |||