Debian Accessibility Project
Summary
Optical Character Recognition (OCR)
Debian Accessibility Optical Character Recognition (OCR)

This metapackage will install packages which are useful for Optical Character Recognition (OCR).

Translate description

Description

For a better overview of the project's availability as a Debian package, each head row has a color code according to this scheme:

If you discover a project which looks like a good candidate for Debian Accessibility to you, or if you have prepared an unofficial Debian package, please do not hesitate to send a description of that project to the Debian Accessibility mailing list

Links to other tasks
Index of all tasks
KDE
X11

Debian Accessibility Optical Character Recognition (OCR) packages

Official Debian packages with high relevance

ebook-speaker
leitor de ebook que lê em voz alta com uma voz sintetizada
Versions of package ebook-speaker
ReleaseVersionArchitectures
buster5.0.0-1amd64,arm64,armhf,i386
jessie2.8.1-1+deb8u1amd64,armel,armhf,i386
sid6.2.0-6amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
trixie6.2.0-6amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bookworm6.2.0-4+deb12u1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bullseye5.5.2-1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
stretch4.1.0-2amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
Debtags of package ebook-speaker:
accessibilityspeech
interfacecommandline
roleprogram
scopeutility
soundplayer
works-withfile
works-with-formatepub
Popcon: 20 users (0 upd.)*
Versions and Archs
 License: DFSG free
Git

Este pacote fornece uma e-reader em linha de comando que lê um texto eletrônico usando síntese de voz. Ele tem uma interface de usuário simples apropriada para terminais em braille.

Atualmente os seguintes formatos são suportados (alguns formatos precisam de pacotes adicionais como sugerido por este pacote):

 AportisDoc
 ASCII mail text
 ASCII text
 Broadband eBooks (BBeB)
 Composite Document File (Microsoft Office Word)
 DAISY3 DTBook
 EPUB ebook data
 GIF image data
 GutenPalm zTXT
 GNU gettext message catalogue
 HTML document
 ISO-8859 text
 JPEG image data
 Microsoft Reader eBook Data
 Microsoft Windows HtmlHelp Data
 Microsoft Word 2007+
 Mobipocket E-book
 MS Windows HtmlHelp Data
 Netpbm PPM data
 OpenDocument Text
 PDF document
 PeanutPress PalmOS
 PNG image data
 POSIX shell script text
 PostScript document
 Rich Text Format
 troff or preprocessor text (e.g. Linux man-pages)
 UTF-8 Unicode mail text
 UTF-8 Unicode text
 WordPerfect
 XML document text
Screenshots of package ebook-speaker
gocr
OCR por linha de comando
Versions of package gocr
ReleaseVersionArchitectures
stretch0.49-2amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
jessie0.49-2amd64,armel,armhf,i386
sid0.52-6.1amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
trixie0.52-6.1amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bookworm0.52-6amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bullseye0.52-3amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
buster0.52-1amd64,arm64,armhf,i386
Debtags of package gocr:
accessibilityocr
interfacecommandline
roleprogram
scopeapplication
useconverting
works-withimage, image:raster, text
Popcon: 193 users (49 upd.)*
Versions and Archs
 License: DFSG free
Git

Este é um programa multiplataforma de OCR ("Optical Character Recognition" - Reconhecimento de Caracteres Óptico).

Pode ler arquivos de imagem pnm, pbm, pgm, ppm, alguns pcx e tga.

Atualmente o programa deve ser capaz de lidar bem com digitalizações que tenham seu texto em uma coluna e não contenham tabelas. Tamanhos de fonte de 20 a 60 pixels são suportados.

Se quiser escrever seu próprio OCR, libgocr é fornecido em um pacote separado. Documentação e o invólucro gráfico são também fornecidos em pacotes separados.
hocr-gtk
GTK+ frontend for Hebrew OCR
Versions of package hocr-gtk
ReleaseVersionArchitectures
jessie0.10.17-2all
buster0.10.18-3all
Debtags of package hocr-gtk:
accessibilityocr
culturehebrew
interfacex11
roleprogram
scopeapplication
uitoolkitgtk
useconverting
works-withimage, image:raster, text
x11application
Popcon: 0 users (0 upd.)*
Versions and Archs
 License: DFSG free
Git

Hocr-gtk is a GTK+ based graphical interface to the libhocr library. It can open multiple image formats and uses aspell for internal spell checking.
lios
Linux intelligent OCR solution
Maintainer: Samuel Thibault
Versions of package lios
ReleaseVersionArchitectures
stretch2.1-2all
sid2.7.2-8all
trixie2.7.2-8all
bookworm2.7.2-6all
bullseye2.7.2-2all
buster2.7-3all
experimental2.7.2+git20221124-0.1all
Popcon: 74 users (7 upd.)*
Versions and Archs
 License: DFSG free
Git

Lios provides a graphical interface on top of the Cuneiform and Tesseract OCR backends to make OCR processing easier for impaired users, with full autorotation, brightness optimization, rectangle selection, audio feedback, etc.
Screenshots of package lios
tesseract-ocr
Tesseract command line OCR tool
Versions of package tesseract-ocr
ReleaseVersionArchitectures
sid5.3.4-1.4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bookworm5.3.0-2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
jessie3.03.03-1amd64,armel,armhf,i386
stretch3.04.01-5amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
stretch-backports4.0.0-2~bpo9+1amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
buster4.0.0-2amd64,arm64,armhf,i386
trixie5.3.4-1.4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bullseye4.1.1-2.1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
upstream5.5.0
Debtags of package tesseract-ocr:
accessibilityocr
interfacecommandline
roleprogram
Popcon: 2095 users (343 upd.)*
Newer upstream!
 License: DFSG free

Tesseract is an open source Optical Character Recognition (OCR) Engine. It can be used directly, or (for programmers) using an API to extract printed text from images. It supports a wide variety of languages. This package includes the command line tool.

Debian packages in contrib or non-free

cuneiform
multi-language OCR system
Versions of package cuneiform
ReleaseVersionArchitectures
buster1.1.0+dfsg-7 (non-free)amd64,arm64,armhf,i386
jessie1.1.0+dfsg-5 (non-free)amd64,i386
sid1.1.0+dfsg-12 (non-free)amd64,arm64,armel,armhf,i386,mips64el,ppc64el
trixie1.1.0+dfsg-12 (non-free)amd64,arm64,armel,armhf,i386,mips64el,ppc64el
bookworm1.1.0+dfsg-9 (non-free)amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el
bullseye1.1.0+dfsg-8 (non-free)amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el
Debtags of package cuneiform:
accessibilityocr
interfacecommandline
roleprogram
scopeutility
useconverting
works-withimage, image:raster
Popcon: 36 users (61 upd.)*
Versions and Archs
 License: non-free
Git

Cuneiform is an OCR system. In addition to text recognition it also does layout analysis and text format recognition.

The following languages are supported: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, French, German, Hungarian, Italian, Latvian, Lithuanian, Polish, Portuguese, Romanian, Russian, Serbian, Slovenian, Spanish, Swedish, Turkish and Ukrainian.
*Popularitycontest results: number of people who use this package regularly (number of people who upgraded this package recently) out of 246295